本项目每月自动从 arXiv 获取最新的论文，基于关键词进行筛选。
点击 'Watch' 按钮可以接收每月自动推送的邮件通知。
本次更新执行命令
D:\a\MyAutoPapers\MyAutoPapers\target\release\my_auto_papers.exe --keywords=
efficient RL,
partial observable markov decision process/pomdp,sparse reward reinforcement learning,
casual RL/counterfactual RL/casual reinforcement learning,
causal inference/causal discovery/counterfactual reasoning,
video super resolution,
knowledge graph/knowledge distillation/knowledge representation/knowledge transfer/knowledge embedding,
combinatorial game theory/xiangqi/chinese chess,
code llm,
speech recognition,
zero shot tracking/few shot tracking/pose tracking/pose estimation,
text to 3d/image to 3d/text to texture,
automated theorem proving/interactive theorem proving/formal verification
--exclude-keywords=multi-agent,multiagent --per-keyword-max-result=8
参数详解
- 关键词：
efficient RL,partial observable markov decision process/pomdp,sparse reward reinforcement learning,casual RL/counterfactual RL/casual reinforcement learning,causal inference/causal discovery/counterfactual reasoning,video super resolution,knowledge graph/knowledge distillation/knowledge representation/knowledge transfer/knowledge embedding,combinatorial game theory/xiangqi/chinese chess,code llm,speech recognition,zero shot tracking/few shot tracking/pose tracking/pose estimation,text to 3d/image to 3d/text to texture,automated theorem proving/interactive theorem proving/formal verification - 排除关键词：
multi-agent,multiagent - 每关键词最大结果：
8 - 目标领域：
cs,stat - 每关键词重试次数：
3
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | When Can Model-Free Reinforcement Learning be Enough for Thinking? | 2025-06-20 | 展开Recent work on large language models has demonstrated the use of model-free reinforcement learning (RL) to train reasoning-like capabilities. The emergence of "thinking" through model-free RL is interesting as thinking actions neither produce reward nor change the external world state to one where the agent is more likely to get reward. This paper seeks to build a domain-independent understanding of when model-free RL will lead to "thinking" as a strategy for reward maximization. To build this understanding, we first introduce a theoretical model which we call a \textit{thought Markov decision process} (MDP). Thought MDPs minimally extend the classical MDP model to include an abstract notion of thought state and thought action. Using the thought MDP model, we prove the importance of policy initialization in determining whether or not thinking emerges and show formally that thought actions are equivalent to the agent choosing to perform a step of policy improvement before continuing to act. We then show that open-source LLMs satisfy the conditions that our theory predicts are necessary for model-free RL to produce thinking-like behavior. Finally, we hypothesize sufficient conditions that would enable thinking to be learned outside of language generation and introduce a toy domain where a combination of multi-task pre-training and designated thought actions enable more data-efficient RL compared to non-thinking agents. |
| 2 | Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement | 2025-06-18 | 展开Recent advancements in large reasoning models (LRMs) have significantly enhanced language models' capabilities in complex problem-solving by emulating human-like deliberative thinking. However, these models often exhibit overthinking (i.e., the generation of unnecessarily verbose and redundant content), which hinders efficiency and inflates inference cost. In this work, we explore the representational and behavioral origins of this inefficiency, revealing that LRMs inherently possess the capacity for more concise reasoning. Empirical analyses show that correct reasoning paths vary significantly in length, and the shortest correct responses often suffice, indicating untapped efficiency potential. Exploiting these findings, we propose two lightweight methods to enhance LRM efficiency. First, we introduce Efficiency Steering, a training-free activation steering technique that modulates reasoning behavior via a single direction in the model's representation space. Second, we develop Self-Rewarded Efficiency RL, a reinforcement learning framework that dynamically balances task accuracy and brevity by rewarding concise correct solutions. Extensive experiments on seven LRM backbones across multiple mathematical reasoning benchmarks demonstrate that our methods significantly reduce reasoning length while preserving or improving task performance. Our results highlight that reasoning efficiency can be improved by leveraging and guiding the intrinsic capabilities of existing models in a self-guided manner. |
| 3 | LearnAlign: Reasoning Data Selection for Reinforcement Learning in Large Language Models Based on Improved Gradient Alignment | 2025-06-13 | 展开Reinforcement learning (RL) has become a key technique for enhancing LLMs' reasoning abilities, yet its data inefficiency remains a major bottleneck. To address this critical yet challenging issue, we present a novel gradient-alignment-based method, named LearnAlign, which intelligently selects the learnable and representative training reasoning data for RL post-training. To overcome the issue of response-length bias in gradient norms, we introduce the data learnability based on the success rate, which can indicate the learning potential of each data point. Experiments across three mathematical reasoning benchmarks demonstrate that our method significantly reduces training data requirements while achieving minor performance degradation or even improving performance compared to full-data training. For example, it reduces data requirements by up to 1,000 data points with better performance (77.53%) than that on the full dataset on GSM8K benchmark (77.04%). Furthermore, we show its effectiveness in the staged RL setting. This work provides valuable insights into data-efficient RL post-training and establishes a foundation for future research in optimizing reasoning data selection. To facilitate future work, we will release code. |
| 4 | Efficient RL-based Cache Vulnerability Exploration by Penalizing Useless Agent Actions | 2025-06-08 | 展开Cache-timing attacks exploit microarchitectural characteristics to leak sensitive data, posing a severe threat to modern systems. Despite its severity, analyzing the vulnerability of a given cache structure against cache-timing attacks is challenging. To this end, a method based on Reinforcement Learning (RL) has been proposed to automatically explore vulnerabilities for a given cache structure. However, a naive RL-based approach suffers from inefficiencies due to the agent performing actions that do not contribute to the exploration. In this paper, we propose a method to identify these useless actions during training and penalize them so that the agent avoids them and the exploration efficiency is improved. Experiments on 17 cache structures show that our training mechanism reduces the number of useless actions by up to 43.08%. This resulted in the reduction of training time by 28% in the base case and 4.84% in the geomean compared to a naive RL-based approach. |
| 5 | Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals | 2025-06-02 | 展开Current Reinforcement Fine-tuning (RFT) paradigms for Large Language Models (LLMs) suffer from sample inefficiency due to the redundant exposure of identical queries under uniform data sampling. While previous work has explored curriculum learning via heuristic difficulty metrics, these strategies exhibit limitations by neglecting the intrinsic learning signals generated by the model itself, thus leading to suboptimal training regimes. In this paper, we identify a model-inherent signal termed angle concentration that effectively reflects an LLM's capacity to learn from specific data. We theoretically and empirically demonstrate a correlation between the angular distribution of token hidden state vectors and the resulting gradient, revealing a learning preference for data exhibiting higher angle concentration. Inspired by this finding, we propose GAIN-RL, a Gradient-driven Angle-Informed Navigated RL framework. By leveraging the model's intrinsic angle concentration signal, GAIN-RL dynamically selects training data in each epoch, ensuring consistently impactful gradient updates and thus significantly enhancing overall training efficiency. Empirical evaluations show that GAIN-RL (GRPO) achieves over a 2.5x acceleration in training efficiency across diverse mathematical and coding tasks and varying model scales. Furthermore, GAIN-RL (GRPO)'s efficient sampling yields data-efficient training, achieving better performance with half the original data compared to vanilla GRPO with full training data. Code is realsed at https://github.com/wangqinsi1/GAINRL/tree/main. |
| 6 | Token-Efficient RL for LLM Reasoning | 2025-04-29 | 展开We propose reinforcement learning (RL) strategies tailored for reasoning in large language models (LLMs) under strict memory and compute limits, with a particular focus on compatibility with LoRA fine-tuning. Building on early policy gradient methods with baseline subtraction, we design critic-free methods that operate on a small, informative subset of output tokens to reduce memory usage and stabilize training. We introduce S-GRPO, a stochastic variant of Group Relative Policy Optimization, and T-SPMO, a token-level prefix matching approach for fine-grained credit assignment. Applied to Qwen2-1.5B, our methods raise accuracy on the SVAMP benchmark from 46% to over 70% and show strong performance on multi-digit multiplication. Surprisingly, full-token GRPO under LoRA fails to improve over the base model, suggesting that selective token-level optimization may act as an implicit regularizer in low-parameter training regimes. |
| 7 | Improving Transformer World Models for Data-Efficient RL | 2025-02-03 | 展开We present an approach to model-based RL that achieves a new state of the art performance on the challenging Craftax-classic benchmark, an open-world 2D survival game that requires agents to exhibit a wide range of general abilities -- such as strong generalization, deep exploration, and long-term reasoning. With a series of careful design choices aimed at improving sample efficiency, our MBRL algorithm achieves a reward of 69.66% after only 1M environment steps, significantly outperforming DreamerV3, which achieves 53.2%, and, for the first time, exceeds human performance of 65.0%. Our method starts by constructing a SOTA model-free baseline, using a novel policy architecture that combines CNNs and RNNs. We then add three improvements to the standard MBRL setup: (a) "Dyna with warmup", which trains the policy on real and imaginary data, (b) "nearest neighbor tokenizer" on image patches, which improves the scheme to create the transformer world model (TWM) inputs, and (c) "block teacher forcing", which allows the TWM to reason jointly about the future tokens of the next timestep. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Active Digital Twins via Active Inference | 2025-06-17 | 展开Digital twins are transforming engineering and applied sciences by enabling real-time monitoring, simulation, and predictive analysis of physical systems and processes. However, conventional digital twins rely primarily on passive data assimilation, which limits their adaptability in uncertain and dynamic environments. This paper introduces the active digital twin paradigm, based on active inference. Active inference is a neuroscience-inspired, Bayesian framework for probabilistic reasoning and predictive modeling that unifies inference, decision-making, and learning under a unique, free energy minimization objective. By formulating the evolution of the active digital twin as a partially observable Markov decision process, the active inference agent continuously refines its generative model through Bayesian updates and forecasts future states and observations. Decision-making emerges from an optimization process that balances pragmatic exploitation (maximizing goal-directed utility) and epistemic exploration or information gain (actively resolving uncertainty). Actions are dynamically planned to minimize expected free energy, which quantifies both the divergence between predicted and preferred future observations, and the epistemic value of expected information gain about hidden states. This approach enables a new level of autonomy and resilience in digital twins, offering superior spontaneous exploration capabilities. The proposed framework is assessed on the health monitoring and predictive maintenance of a railway bridge. |
| 2 | Forward and Backward Simulations for Partially Observable Probability | 2025-06-10 | 展开Data refinement is the standard extension of a refinement relation from programs to datatypes (i.e. a behavioural subtyping relation). Forward/backward simulations provide a tractable method for establishing data refinement, and have been thoroughly studied for nondeterministic programs. However, for standard models of mixed probability and nondeterminism, ordinary assignment statements may not commute with (variable-disjoint) program fragments. This (1) invalidates a key assumption underlying the soundness of simulations, and (2) prevents modelling probabilistic datatypes with encapsulated state. We introduce a weakest precondition semantics for Kuifje$_\sqcap$, a language for partially observable Markov decision processes, using so-called loss (function) transformers. We prove soundness of forward/backward simulations in this richer setting, modulo healthiness conditions with a remarkable duality: forward simulations cannot leak information, and backward simulations cannot exploit leaked information. |
| 3 | $τ^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment | 2025-06-09 | 展开Existing benchmarks for conversational AI agents simulate single-control environments, where only the AI agent can use tools to interact with the world, while the user remains a passive information provider. This differs from real-world scenarios like technical support, where users need to actively participate in modifying the state of the (shared) world. In order to address this gap, we introduce |
| 4 | Robust Finite-Memory Policy Gradients for Hidden-Model POMDPs | 2025-05-14 | 展开Partially observable Markov decision processes (POMDPs) model specific environments in sequential decision-making under uncertainty. Critically, optimal policies for POMDPs may not be robust against perturbations in the environment. Hidden-model POMDPs (HM-POMDPs) capture sets of different environment models, that is, POMDPs with a shared action and observation space. The intuition is that the true model is hidden among a set of potential models, and it is unknown which model will be the environment at execution time. A policy is robust for a given HM-POMDP if it achieves sufficient performance for each of its POMDPs.We compute such robust policies by combining two orthogonal techniques: (1) a deductive formal verification technique that supports tractable robust policy evaluation by computing a worst-case POMDP within the HM-POMDP, and (2) subgradient ascent to optimize the candidate policy for a worst-case POMDP. The empirical evaluation shows that, compared to various baselines, our approach (1) produces policies that are more robust and generalize better to unseen POMDPs, and (2) scales to HM-POMDPs that consist of over a hundred thousand environments. |
| 5 | Learning Attentive Neural Processes for Planning with Pushing Actions | 2025-04-24 | 展开Our goal is to enable robots to plan sequences of tabletop actions to push a block with unknown physical properties to a desired goal pose. We approach this problem by learning the constituent models of a Partially-Observable Markov Decision Process (POMDP), where the robot can observe the outcome of a push, but the physical properties of the block that govern the dynamics remain unknown. A common solution approach is to train an observation model in a supervised fashion, and do inference with a general inference technique such as particle filters. However, supervised training requires knowledge of the relevant physical properties that determine the problem dynamics, which we do not assume to be known. Planning also requires simulating many belief updates, which becomes expensive when using particle filters to represent the belief. We propose to learn an Attentive Neural Process that computes the belief over a learned latent representation of the relevant physical properties given a history of actions. To address the pushing planning problem, we integrate a trained Neural Process with a double-progressive widening sampling strategy. Simulation results indicate that Neural Process Tree with Double Progressive Widening (NPT-DPW) generates better-performing plans faster than traditional particle-filter methods that use a supervised-trained observation model, even in complex pushing scenarios. |
| 6 | POPGym Arcade: Parallel Pixelated POMDPs | 2025-03-03 | 展开We present the POPGym Arcade, a collection of hardware-accelerated, pixel-based environments with shared observation and action spaces. Each environment includes fully and partially observable variants, enabling counterfactual studies on partial observability. We also introduce mathematical tools for analyzing policies under partial observability, which reveal how agents recall past information to make decisions. Our analysis shows (1) that controlling for partial observability is critical and (2) that agents with long-term memory learn brittle policies that struggle to generalize. Finally, we demonstrate that recurrent policies can be "poisoned" by old, out-of-distribution observations, with implications for sim-to-real transfer, imitation learning, and offline reinforcement learning. |
| 7 | Map Space Belief Prediction for Manipulation-Enhanced Mapping | 2025-02-28 | 展开Searching for objects in cluttered environments requires selecting efficient viewpoints and manipulation actions to remove occlusions and reduce uncertainty in object locations, shapes, and categories. In this work, we address the problem of manipulation-enhanced semantic mapping, where a robot has to efficiently identify all objects in a cluttered shelf. Although Partially Observable Markov Decision Processes~(POMDPs) are standard for decision-making under uncertainty, representing unstructured interactive worlds remains challenging in this formalism. To tackle this, we define a POMDP whose belief is summarized by a metric-semantic grid map and propose a novel framework that uses neural networks to perform map-space belief updates to reason efficiently and simultaneously about object geometries, locations, categories, occlusions, and manipulation physics. Further, to enable accurate information gain analysis, the learned belief updates should maintain calibrated estimates of uncertainty. Therefore, we propose Calibrated Neural-Accelerated Belief Updates (CNABUs) to learn a belief propagation model that generalizes to novel scenarios and provides confidence-calibrated predictions for unknown areas. Our experiments show that our novel POMDP planner improves map completeness and accuracy over existing methods in challenging simulations and successfully transfers to real-world cluttered shelves in zero-shot fashion. |
| 8 | Limit-sure reachability for small memory policies in POMDPs is NP-complete | 2024-12-01 | 展开A standard model that arises in several applications in sequential decision making is partially observable Markov decision processes (POMDPs) where a decision-making agent interacts with an uncertain environment. A basic objective in such POMDPs is the reachability objective, where given a target set of states, the goal is to eventually arrive at one of them. The limit-sure problem asks whether reachability can be ensured with probability arbitrarily close to 1. In general, the limit-sure reachability problem for POMDPs is undecidable. However, in many practical cases the most relevant question is the existence of policies with a small amount of memory. In this work, we study the limit-sure reachability problem for POMDPs with a fixed amount of memory. We establish that the computational complexity of the problem is NP-complete. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | SuperRL: Reinforcement Learning with Supervision to Boost Language Model Reasoning | 2025-06-01 | 展开Large language models are increasingly used for complex reasoning tasks where high-quality offline data such as expert-annotated solutions and distilled reasoning traces are often available. However, in environments with sparse rewards, reinforcement learning struggles to sample successful trajectories, leading to inefficient learning. At the same time, these offline trajectories that represent correct reasoning paths are not utilized by standard on-policy reinforcement learning methods. To address this limitation, we propose SuperRL, a unified training framework that adaptively incorporates offline supervision into reinforcement learning. SuperRL introduces an Adaptive Switch to detect sparse reward conditions and activates a Hybrid Actor when necessary. The Hybrid Actor integrates policy gradient and supervised learning objectives at the loss level, enabling the model to benefit from accurate offline reasoning signals while maintaining the exploratory capacity of reinforcement learning. Experiments on a range of reasoning benchmarks show that SuperRL consistently outperforms standard reinforcement learning by improving sample efficiency, generalization, and robustness under sparse rewards. |
| 2 | DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning | 2025-05-26 | 展开Sparse-reward reinforcement learning (RL) can model a wide range of highly complex tasks. Solving sparse-reward tasks is RL's core premise - requiring efficient exploration coupled with long-horizon credit assignment - and overcoming these challenges is key for building self-improving agents with superhuman ability. We argue that solving complex and high-dimensional tasks requires solving simpler tasks that are relevant to the target task. In contrast, most prior work designs strategies for selecting exploratory tasks with the objective of solving any task, making exploration of challenging high-dimensional, long-horizon tasks intractable. We find that the sense of direction, necessary for effective exploration, can be extracted from existing RL algorithms, without needing any prior information. Based on this finding, we propose a method for directed sparse-reward goal-conditioned very long-horizon RL (DISCOVER), which selects exploratory goals in the direction of the target task. We connect DISCOVER to principled exploration in bandits, formally bounding the time until the target task becomes achievable in terms of the agent's initial distance to the target, but independent of the volume of the space of all tasks. Empirically, we perform a thorough evaluation in high-dimensional environments. We find that the directed goal selection of DISCOVER solves exploration problems that are beyond the reach of prior state-of-the-art exploration methods in RL. |
| 3 | STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs | 2025-05-21 | 展开Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, yet they lag significantly behind humans in spatial reasoning. We investigate this gap through Transformation-Driven Visual Reasoning (TVR), a challenging task requiring identification of object transformations across images under varying viewpoints. While traditional Supervised Fine-Tuning (SFT) fails to generate coherent reasoning paths in cross-view settings, sparse-reward Reinforcement Learning (RL) suffers from inefficient exploration and slow convergence. To address these limitations, we propose STAR-R1, a novel framework that integrates a single-stage RL paradigm with a fine-grained reward mechanism tailored for TVR. Specifically, STAR-R1 rewards partial correctness while penalizing excessive enumeration and passive inaction, enabling efficient exploration and precise reasoning. Comprehensive evaluations demonstrate that STAR-R1 achieves state-of-the-art performance across all 11 metrics, outperforming SFT by 23% in cross-view scenarios. Further analysis reveals STAR-R1's anthropomorphic behavior and highlights its unique ability to compare all objects for improving spatial reasoning. Our work provides critical insights in advancing the research of MLLMs and reasoning models. The codes, model weights, and data will be publicly available at https://github.com/zongzhao23/STAR-R1. |
| 4 | Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model | 2025-03-14 | 展开Uncertainty quantification is a critical aspect of reinforcement learning and deep learning, with numerous applications ranging from efficient exploration and stable offline reinforcement learning to outlier detection in medical diagnostics. The scale of modern neural networks, however, complicates the use of many theoretically well-motivated approaches such as full Bayesian inference. Approximate methods like deep ensembles can provide reliable uncertainty estimates but still remain computationally expensive. In this work, we propose contextual similarity distillation, a novel approach that explicitly estimates the variance of an ensemble of deep neural networks with a single model, without ever learning or evaluating such an ensemble in the first place. Our method builds on the predictable learning dynamics of wide neural networks, governed by the neural tangent kernel, to derive an efficient approximation of the predictive variance of an infinite ensemble. Specifically, we reinterpret the computation of ensemble variance as a supervised regression problem with kernel similarities as regression targets. The resulting model can estimate predictive variance at inference time with a single forward pass, and can make use of unlabeled target-domain data or data augmentations to refine its uncertainty estimates. We empirically validate our method across a variety of out-of-distribution detection benchmarks and sparse-reward reinforcement learning environments. We find that our single-model method performs competitively and sometimes superior to ensemble-based baselines and serves as a reliable signal for efficient exploration. These results, we believe, position contextual similarity distillation as a principled and scalable alternative for uncertainty quantification in reinforcement learning and general deep learning. |
| 5 | Hedging with Sparse Reward Reinforcement Learning | 2025-03-06 | 展开Derivatives, as a critical class of financial instruments, isolate and trade the price attributes of risk assets such as stocks, commodities, and indices, aiding risk management and enhancing market efficiency. However, traditional hedging models, constrained by assumptions such as continuous trading and zero transaction costs, fail to satisfy risk control requirements in complex and uncertain real-world markets. With advances in computing technology and deep learning, data-driven trading strategies are becoming increasingly prevalent. This thesis proposes a derivatives hedging framework integrating deep learning and reinforcement learning. The framework comprises a probabilistic forecasting model and a hedging agent, enabling market probability prediction, derivative pricing, and hedging. Specifically, we design a spatiotemporal attention-based probabilistic financial time series forecasting Transformer to address the scarcity of derivatives hedging data. A low-rank attention mechanism compresses high-dimensional assets into a low-dimensional latent space, capturing nonlinear asset relationships. The Transformer models sequential dependencies within this latent space, improving market probability forecasts and constructing an online training environment for downstream hedging tasks. Additionally, we incorporate generalized geometric Brownian motion to develop a risk-neutral pricing approach for derivatives. We model derivatives hedging as a reinforcement learning problem with sparse rewards and propose a behavior cloning-based recurrent proximal policy optimization (BC-RPPO) algorithm. This pretraining-finetuning framework significantly enhances the hedging agent's performance. Numerical experiments in the U.S. and Chinese financial markets demonstrate our method's superiority over traditional approaches. |
| 6 | Dense Dynamics-Aware Reward Synthesis: Integrating Prior Experience with Demonstrations | 2024-12-02 | 展开Many continuous control problems can be formulated as sparse-reward reinforcement learning (RL) tasks. In principle, online RL methods can automatically explore the state space to solve each new task. However, discovering sequences of actions that lead to a non-zero reward becomes exponentially more difficult as the task horizon increases. Manually shaping rewards can accelerate learning for a fixed task, but it is an arduous process that must be repeated for each new environment. We introduce a systematic reward-shaping framework that distills the information contained in 1) a task-agnostic prior data set and 2) a small number of task-specific expert demonstrations, and then uses these priors to synthesize dense dynamics-aware rewards for the given task. This supervision substantially accelerates learning in our experiments, and we provide analysis demonstrating how the approach can effectively guide online learning agents to faraway goals. |
| 7 | Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning | 2023-09-08 | 展开Exploration in sparse-reward reinforcement learning is difficult due to the requirement of long, coordinated sequences of actions in order to achieve any reward. Moreover, in continuous action spaces there are an infinite number of possible actions, which only increases the difficulty of exploration. One class of methods designed to address these issues forms temporally extended actions, often called skills, from interaction data collected in the same domain, and optimizes a policy on top of this new action space. Typically such methods require a lengthy pretraining phase, especially in continuous action spaces, in order to form the skills before reinforcement learning can begin. Given prior evidence that the full range of the continuous action space is not required in such tasks, we propose a novel approach to skill-generation with two components. First we discretize the action space through clustering, and second we leverage a tokenization technique borrowed from natural language processing to generate temporally extended actions. Such a method outperforms baselines for skill-generation in several challenging sparse-reward domains, and requires orders-of-magnitude less computation in skill-generation and online rollouts. Our code is available at \url{https://github.com/dyunis/subwords_as_skills}. |
| 8 | Language Reward Modulation for Pretraining Reinforcement Learning | 2023-08-23 | 展开Using learned reward functions (LRFs) as a means to solve sparse-reward reinforcement learning (RL) tasks has yielded some steady progress in task-complexity through the years. In this work, we question whether today's LRFs are best-suited as a direct replacement for task rewards. Instead, we propose leveraging the capabilities of LRFs as a pretraining signal for RL. Concretely, we propose $\textbf{LA}$nguage Reward $\textbf{M}$odulated $\textbf{P}$retraining (LAMP) which leverages the zero-shot capabilities of Vision-Language Models (VLMs) as a |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Should I Trust You? Detecting Deception in Negotiations using Counterfactual RL | 2025-02-18 | 展开An increasingly common socio-technical problem is people being taken in by offers that sound ``too good to be true'', where persuasion and trust shape decision-making. This paper investigates how \abr{ai} can help detect these deceptive scenarios. We analyze how humans strategically deceive each other in \textit{Diplomacy}, a board game that requires both natural language communication and strategic reasoning. This requires extracting logical forms of proposed agreements in player communications and computing the relative rewards of the proposal using agents' value functions. Combined with text-based features, this can improve our deception detection. Our method detects human deception with a high precision when compared to a Large Language Model approach that flags many true messages as deceptive. Future human-\abr{ai} interaction tools can build on our methods for deception detection by triggering \textit{friction} to give users a chance of interrogating suspicious proposals. |
| 2 | Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation | 2020-12-16 | 展开Reinforcement learning (RL) algorithms usually require a substantial amount of interaction data and perform well only for specific tasks in a fixed environment. In some scenarios such as healthcare, however, usually only few records are available for each patient, and patients may show different responses to the same treatment, impeding the application of current RL algorithms to learn optimal policies. To address the issues of mechanism heterogeneity and related data scarcity, we propose a data-efficient RL algorithm that exploits structural causal models (SCMs) to model the state dynamics, which are estimated by leveraging both commonalities and differences across subjects. The learned SCM enables us to counterfactually reason what would have happened had another treatment been taken. It helps avoid real (possibly risky) exploration and mitigates the issue that limited experiences lead to biased policies. We propose counterfactual RL algorithms to learn both population-level and individual-level policies. We show that counterfactual outcomes are identifiable under mild conditions and that Q- learning on the counterfactual-based augmented data set converges to the optimal value function. Experimental results on synthetic and real-world data demonstrate the efficacy of the proposed approach. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | When Additive Noise Meets Unobserved Mediators: Bivariate Denoising Diffusion for Causal Discovery | 2025-06-29 | 展开Distinguishing cause and effect from bivariate observational data is a foundational problem in many disciplines, but challenging without additional assumptions. Additive noise models (ANMs) are widely used to enable sample-efficient bivariate causal discovery. However, conventional ANM-based methods fail when unobserved mediators corrupt the causal relationship between variables. This paper makes three key contributions: first, we rigorously characterize why standard ANM approaches break down in the presence of unmeasured mediators. Second, we demonstrate that prior solutions for hidden mediation are brittle in finite sample settings, limiting their practical utility. To address these gaps, we propose Bivariate Denoising Diffusion (BiDD) for causal discovery, a method designed to handle latent noise introduced by unmeasured mediators. Unlike prior methods that infer directionality through mean squared error loss comparisons, our approach introduces a novel independence test statistic: during the noising and denoising processes for each variable, we condition on the other variable as input and evaluate the independence of the predicted noise relative to this input. We prove asymptotic consistency of BiDD under the ANM, and conjecture that it performs well under hidden mediation. Experiments on synthetic and real-world data demonstrate consistent performance, outperforming existing methods in mediator-corrupted settings while maintaining strong performance in mediator-free settings. |
| 2 | Auto-Doubly Robust Estimation of Causal Effects on a Network | 2025-06-29 | 展开This paper develops new methods for causal inference in observational studies on a single large network of interconnected units, addressing two key challenges: long-range dependence among units and the presence of general interference. We introduce a novel network version of Augmented Inverse Propensity Weighted, which combines propensity score and outcome models defined on the network to achieve doubly robust identification and estimation of both direct and spillover causal effects. Under a network version of conditional ignorability, the proposed approach identifies the expected potential outcome for a unit given the treatment assignment vector for its network neighborhood up to a user-specified distance, while marginalizing over treatment assignments for the rest of the network. By introducing two additional assumptions on the outcome, we establish a new doubly robust identification result for the expected potential outcome under a hypothetical intervention on the treatment assignment vector for the entire network. Under a union of Chain Graph models - one governing the propensity model and the other the outcome model - we propose a corresponding semiparametric estimator based on parametric models naturally arising from the chain graph representation of the network. We formally prove that, under weak network dependence, the proposed estimators are asymptotically normal and we characterize the impact of model misspecification on the asymptotic variance. Extensive simulation studies highlight the practical relevance of our approach. We further demonstrate its application in an empirical analysis of the NNAHRAY study, evaluating the impact of incarceration on individual socioeconomic outcomes in Brooklyn, New York. |
| 3 | P-CRE-DML: A Novel Approach for Causal Inference in Non-Linear Panel Data | 2025-06-29 | 展开This paper introduces a novel Proxy-Enhanced Correlated Random Effects Double Machine Learning (P-CRE-DML) framework to estimate causal effects in panel data with non-linearities and unobserved heterogeneity. Combining Double Machine Learning (DML, Chernozhukov et al., 2018), Correlated Random Effects (CRE, Mundlak, 1978), and lagged variables (Arellano & Bond, 1991) and innovating within the CRE-DML framework (Chernozhukov et al., 2022; Clarke & Polselli, 2025; Fuhr & Papies, 2024), we apply P-CRE-DML to investigate the effect of social trust on GDP growth across 89 countries (2010-2020). We find positive and statistically significant relationship between social trust and economic growth. This aligns with prior findings on trust-growth relationship (e.g., Knack & Keefer, 1997). Furthermore, a Monte Carlo simulation demonstrates P-CRE-DML's advantage in terms of lower bias over CRE-DML and System GMM. P-CRE-DML offers a robust and flexible alternative for panel data causal inference, with applications beyond economic growth. |
| 4 | Token Activation Map to Visually Explain Multimodal LLMs | 2025-06-29 | 展开Multimodal large language models (MLLMs) are broadly empowering various fields. Despite their advancements, the explainability of MLLMs remains less explored, hindering deeper understanding, model credibility, and effective visualization. Unlike conventional vision models (e.g., CNNs, ViTs, CLIP) that produce a single output, MLLMs generate sequences of tokens progressively, where each generated token depends on the previous context. Therefore, earlier context tokens can introduce redundant activations that interfere with the explanation of later tokens beyond their original information. Existing studies often overlook this issue, but our observations reveal that these redundant correlations can significantly hurt the reliability of explanations. To address this, we propose an estimated causal inference method to mitigate the interference of context to achieve high-quality MLLM explanation, with a novel rank Gaussian filter to further reduce activation noises. We term this method Token Activation Map (TAM) to highlight the consideration of interactions between tokens. TAM also indicates that it excels at explaining multiple tokens of MLLM, which is different from the Class Activation Map (CAM) for a single prediction. Our TAM method significantly outperforms existing SoTA methods, showcasing high-quality visualization results that can be utilized for various scenarios, such as object localization, failure case analysis, video visualization, MLLMs visual comparison, and model understanding (e.g., color, shape, action, location, visual reasoning, multi-turn conversation, etc). The code is available atgithub.com/xmed-lab/TAM. |
| 5 | Resilient-Native and Intelligent Next-Generation Wireless Systems: Key Enablers, Foundations, and Applications | 2025-06-28 | 展开Just like power, water, and transportation systems, wireless networks are a crucial societal infrastructure. As natural and human-induced disruptions continue to grow, wireless networks must be resilient. This requires them to withstand and recover from unexpected adverse conditions, shocks, unmodeled disturbances and cascading failures. Unlike robustness and reliability, resilience is based on the understanding that disruptions will inevitably happen. Resilience, as elasticity, focuses on the ability to bounce back to favorable states, while resilience as plasticity involves agents and networks that can flexibly expand their states and hypotheses through real-time adaptation and reconfiguration. This situational awareness and active preparedness, adapting world models and counterfactually reasoning about potential system failures and the best responses, is a core aspect of resilience. This article will first disambiguate resilience from reliability and robustness, before delving into key mathematical foundations of resilience grounded in abstraction, compositionality and emergence. Subsequently, we focus our attention on a plethora of techniques and methodologies pertaining to the unique characteristics of resilience, as well as their applications through a comprehensive set of use cases. Ultimately, the goal of this paper is to establish a unified foundation for understanding, modeling, and engineering resilience in wireless communication systems, while laying a roadmap for the next-generation of resilient-native and intelligent wireless systems. |
| 6 | Can Video Large Multimodal Models Think Like Doubters-or Double-Down: A Study on Defeasible Video Entailment | 2025-06-27 | 展开Video Large Multimodal Models (VLMMs) have made impressive strides in understanding video content, but they often struggle with abstract and adaptive reasoning-the ability to revise their interpretations when new information emerges. In reality, conclusions are rarely set in stone; additional context can strengthen or weaken an initial inference. To address this, we introduce Defeasible Video Entailment (DVidE), a new task that challenges models to think like doubters, constantly updating their reasoning based on evolving evidence. In DVidE, given a video premise and a textual hypothesis, models must determine whether a new update strengthens or weakens the hypothesis (classification version) or generate a coherent update that modifies the entailment relationship (generation version). For solving the classification task, we propose the Chain of Counterfactual Thought framework, utilizing counterfactual reasoning, ASR-enhanced video content, and rationale refinement to reduce inference bias. For the generation task, we develop a framework that combines ASR output with a Large Language Model (LLM) to produce coherent, contextually relevant updates aligned with the intended strengthener or weakener goals. Additionally, we introduce a novel benchmark dataset, with strengthener/weakener annotations and an LLM-based evaluation metric specifically designed for assessing generative performance. Experimental results demonstrate significant improvements, highlighting our proposed method in enhancing dynamic reasoning capabilities of VLMMs. |
| 7 | Less Greedy Equivalence Search | 2025-06-27 | 展开Greedy Equivalence Search (GES) is a classic score-based algorithm for causal discovery from observational data. In the sample limit, it recovers the Markov equivalence class of graphs that describe the data. Still, it faces two challenges in practice: computational cost and finite-sample accuracy. In this paper, we develop Less Greedy Equivalence Search (LGES), a variant of GES that retains its theoretical guarantees while partially addressing these limitations. LGES modifies the greedy step: rather than always applying the highest-scoring insertion, it avoids edge insertions between variables for which the score implies some conditional independence. This more targeted search yields up to a (10)-fold speed-up and a substantial reduction in structural error relative to GES. Moreover, LGES can guide the search using prior assumptions, while correcting these assumptions when contradicted by the data. Finally, LGES can exploit interventional data to refine the learned observational equivalence class. We prove that LGES recovers the true equivalence class in the sample limit from observational and interventional data, even with misspecified prior assumptions. Experiments demonstrate that LGES outperforms GES and other baselines in speed, accuracy, and robustness to misspecified assumptions. Our code is available at https://github.com/CausalAILab/lges. |
| 8 | HalluSegBench: Counterfactual Visual Reasoning for Segmentation Hallucination Evaluation | 2025-06-26 | 展开Recent progress in vision-language segmentation has significantly advanced grounded visual understanding. However, these models often exhibit hallucinations by producing segmentation masks for objects not grounded in the image content or by incorrectly labeling irrelevant regions. Existing evaluation protocols for segmentation hallucination primarily focus on label or textual hallucinations without manipulating the visual context, limiting their capacity to diagnose critical failures. In response, we introduce HalluSegBench, the first benchmark specifically designed to evaluate hallucinations in visual grounding through the lens of counterfactual visual reasoning. Our benchmark consists of a novel dataset of 1340 counterfactual instance pairs spanning 281 unique object classes, and a set of newly introduced metrics that quantify hallucination sensitivity under visually coherent scene edits. Experiments on HalluSegBench with state-of-the-art vision-language segmentation models reveal that vision-driven hallucinations are significantly more prevalent than label-driven ones, with models often persisting in false segmentation, highlighting the need for counterfactual reasoning to diagnose grounding fidelity. |
| 9 | Active Inference AI Systems for Scientific Discovery | 2025-06-26 | 展开The rapid evolution of artificial intelligence has led to expectations of transformative scientific discovery, yet current systems remain fundamentally limited by their operational architectures, brittle reasoning mechanisms, and their separation from experimental reality. Building on earlier work, we contend that progress in AI-driven science now depends on closing three fundamental gaps -- the abstraction gap, the reasoning gap, and the reality gap -- rather than on model size/data/test time compute. Scientific reasoning demands internal representations that support simulation of actions and response, causal structures that distinguish correlation from mechanism, and continuous calibration. We define active inference AI systems for scientific discovery as those that (i) maintain long-lived research memories grounded in causal self-supervised foundation models, (ii) symbolic or neuro-symbolic planners equipped with Bayesian guardrails, (iii) grow persistent knowledge graphs where thinking generates novel conceptual nodes, reasoning establishes causal edges, and real-world interaction prunes false connections while strengthening verified pathways, and (iv) refine their internal representations through closed-loop interaction with both high-fidelity simulators and automated laboratories - an operational loop where mental simulation guides action and empirical surprise reshapes understanding. In essence, we outline an architecture where discovery arises from the interplay between internal models that enable counterfactual reasoning and external validation that grounds hypotheses in reality. It is also argued that the inherent ambiguity in feedback from simulations and experiments, and underlying uncertainties makes human judgment indispensable, not as a temporary scaffold but as a permanent architectural component. |
| 10 | Lower Bounds on the Size of Markov Equivalence Classes | 2025-06-26 | 展开Causal discovery algorithms typically recover causal graphs only up to their Markov equivalence classes unless additional parametric assumptions are made. The sizes of these equivalence classes reflect the limits of what can be learned about the underlying causal graph from purely observational data. Under the assumptions of acyclicity, causal sufficiency, and a uniform model prior, Markov equivalence classes are known to be small on average. In this paper, we show that this is no longer the case when any of these assumptions is relaxed. Specifically, we prove exponentially large lower bounds for the expected size of Markov equivalence classes in three settings: sparse random directed acyclic graphs, uniformly random acyclic directed mixed graphs, and uniformly random directed cyclic graphs. |
| 11 | Learning Causally Predictable Outcomes from Psychiatric Longitudinal Data | 2025-06-19 | 展开Causal inference in longitudinal biomedical data remains a central challenge, especially in psychiatry, where symptom heterogeneity and latent confounding frequently undermine classical estimators. Most existing methods for treatment effect estimation presuppose a fixed outcome variable and address confounding through observed covariate adjustment. However, the assumption of unconfoundedness may not hold for a fixed outcome in practice. To address this foundational limitation, we directly optimize the outcome definition to maximize causal identifiability. Our DEBIAS (Durable Effects with Backdoor-Invariant Aggregated Symptoms) algorithm learns non-negative, clinically interpretable weights for outcome aggregation, maximizing durable treatment effects and empirically minimizing both observed and latent confounding by leveraging the time-limited direct effects of prior treatments in psychiatric longitudinal data. The algorithm also furnishes an empirically verifiable test for outcome unconfoundedness. DEBIAS consistently outperforms state-of-the-art methods in recovering causal effects for clinically interpretable composite outcomes across comprehensive experiments in depression and schizophrenia. |
| 12 | An introduction to Causal Modelling | 2025-06-19 | 展开This tutorial provides a concise introduction to modern causal modeling by integrating potential outcomes and graphical methods. We motivate causal questions such as counterfactual reasoning under interventions and define binary treatments and potential outcomes. We discuss causal effect measures-including average treatment effects on the treated and on the untreated-and choices of effect scales for binary outcomes. We derive identification in randomized experiments under exchangeability and consistency, and extend to stratification and blocking designs. We present inverse probability weighting with propensity score estimation and robust inference via sandwich estimators. Finally, we introduce causal graphs, d-separation, the backdoor criterion, single-world intervention graphs, and structural equation models, showing how graphical and potential-outcome approaches complement each other. Emphasis is placed on clear notation, intuitive explanations, and practical examples for applied researchers. |
| 13 | Exploring Big Five Personality and AI Capability Effects in LLM-Simulated Negotiation Dialogues | 2025-06-19 | 展开This paper presents an evaluation framework for agentic AI systems in mission-critical negotiation contexts, addressing the need for AI agents that can adapt to diverse human operators and stakeholders. Using Sotopia as a simulation testbed, we present two experiments that systematically evaluated how personality traits and AI agent characteristics influence LLM-simulated social negotiation outcomes--a capability essential for a variety of applications involving cross-team coordination and civil-military interactions. Experiment 1 employs causal discovery methods to measure how personality traits impact price bargaining negotiations, through which we found that Agreeableness and Extraversion significantly affect believability, goal achievement, and knowledge acquisition outcomes. Sociocognitive lexical measures extracted from team communications detected fine-grained differences in agents' empathic communication, moral foundations, and opinion patterns, providing actionable insights for agentic AI systems that must operate reliably in high-stakes operational scenarios. Experiment 2 evaluates human-AI job negotiations by manipulating both simulated human personality and AI system characteristics, specifically transparency, competence, adaptability, demonstrating how AI agent trustworthiness impact mission effectiveness. These findings establish a repeatable evaluation methodology for experimenting with AI agent reliability across diverse operator personalities and human-agent team dynamics, directly supporting operational requirements for reliable AI systems. Our work advances the evaluation of agentic AI workflows by moving beyond standard performance metrics to incorporate social dynamics essential for mission success in complex operations. |
| 14 | DeVisE: Behavioral Testing of Medical Large Language Models | 2025-06-18 | 展开Large language models (LLMs) are increasingly used in clinical decision support, yet current evaluation methods often fail to distinguish genuine medical reasoning from superficial patterns. We introduce DeVisE (Demographics and Vital signs Evaluation), a behavioral testing framework for probing fine-grained clinical understanding. We construct a dataset of ICU discharge notes from MIMIC-IV, generating both raw (real-world) and template-based (synthetic) versions with controlled single-variable counterfactuals targeting demographic (age, gender, ethnicity) and vital sign attributes. We evaluate five LLMs spanning general-purpose and medically fine-tuned variants, under both zero-shot and fine-tuned settings. We assess model behavior via (1) input-level sensitivity - how counterfactuals alter the likelihood of a note; and (2) downstream reasoning - how they affect predicted hospital length-of-stay. Our results show that zero-shot models exhibit more coherent counterfactual reasoning patterns, while fine-tuned models tend to be more stable yet less responsive to clinically meaningful changes. Notably, demographic factors subtly but consistently influence outputs, emphasizing the importance of fairness-aware evaluation. This work highlights the utility of behavioral testing in exposing the reasoning strategies of clinical LLMs and informing the design of safer, more transparent medical AI systems. |
| 15 | Resilient-native and Intelligent NextG Systems | 2025-06-15 | 展开Just like power, water and transportation systems, wireless networks are a crucial societal infrastructure. As natural and human-induced disruptions continue to grow, wireless networks must be resilient to unforeseen events, able to withstand and recover from unexpected adverse conditions, shocks, unmodeled disturbances and cascading failures. Despite its critical importance, resilience remains an elusive concept, with its mathematical foundations still underdeveloped. Unlike robustness and reliability, resilience is premised on the fact that disruptions will inevitably happen. Resilience, in terms of elasticity, focuses on the ability to bounce back to favorable states, while resilience as plasticity involves agents (or networks) that can flexibly expand their states, hypotheses and course of actions, by transforming through real-time adaptation and reconfiguration. This constant situational awareness and vigilance of adapting world models and counterfactually reasoning about potential system failures and the corresponding best responses, is a core aspect of resilience. This article seeks to first define resilience and disambiguate it from reliability and robustness, before delving into the mathematics of resilience. Finally, the article concludes by presenting nuanced metrics and discussing trade-offs tailored to the unique characteristics of network resilience. |
| 16 | LLMs Struggle to Perform Counterfactual Reasoning with Parametric Knowledge | 2025-06-15 | 展开Large Language Models have been shown to contain extensive world knowledge in their parameters, enabling impressive performance on many knowledge intensive tasks. However, when deployed in novel settings, LLMs often encounter situations where they must integrate parametric knowledge with new or unfamiliar information. In this work, we explore whether LLMs can combine knowledge in-context with their parametric knowledge through the lens of counterfactual reasoning. Through synthetic and real experiments in multi-hop reasoning problems, we show that LLMs generally struggle with counterfactual reasoning, often resorting to exclusively using their parametric knowledge. Moreover, we show that simple post-hoc finetuning can struggle to instill counterfactual reasoning ability -- often leading to degradation in stored parametric knowledge. Ultimately, our work reveals important limitations of current LLM's abilities to re-purpose parametric knowledge in novel settings. |
| 17 | What Makes Treatment Effects Identifiable? Characterizations and Estimators Beyond Unconfoundedness | 2025-06-04 | 展开Most of the widely used estimators of the average treatment effect (ATE) in causal inference rely on the assumptions of unconfoundedness and overlap. Unconfoundedness requires that the observed covariates account for all correlations between the outcome and treatment. Overlap requires the existence of randomness in treatment decisions for all individuals. Nevertheless, many types of studies frequently violate unconfoundedness or overlap, for instance, observational studies with deterministic treatment decisions - popularly known as Regression Discontinuity designs - violate overlap. In this paper, we initiate the study of general conditions that enable the identification of the average treatment effect, extending beyond unconfoundedness and overlap. In particular, following the paradigm of statistical learning theory, we provide an interpretable condition that is sufficient and necessary for the identification of ATE. Moreover, this condition also characterizes the identification of the average treatment effect on the treated (ATT) and can be used to characterize other treatment effects as well. To illustrate the utility of our condition, we present several well-studied scenarios where our condition is satisfied and, hence, we prove that ATE can be identified in regimes that prior works could not capture. For example, under mild assumptions on the data distributions, this holds for the models proposed by Tan (2006) and Rosenbaum (2002), and the Regression Discontinuity design model introduced by Thistlethwaite and Campbell (1960). For each of these scenarios, we also show that, under natural additional assumptions, ATE can be estimated from finite samples. We believe these findings open new avenues for bridging learning-theoretic insights and causal inference methodologies, particularly in observational studies with complex treatment mechanisms. |
| 18 | Local Markov Equivalence and Local Causal Discovery for Identifying Controlled Direct Effects | 2025-05-05 | 展开Understanding and identifying controlled direct effects (CDEs) is crucial across numerous scientific domains, including public health. While existing methods can identify these effects from causal directed acyclic graphs (DAGs), the true underlying structure is often unknown in practice. Essential graphs, which represent a Markov equivalence class of DAGs characterized by the same set of |
| 19 | Linear scaling causal discovery from high-dimensional time series by dynamical community detection | 2025-01-18 | 展开Understanding which parts of a dynamical system cause each other is extremely relevant in fundamental and applied sciences. However, inferring causal links from observational data, namely without direct manipulations of the system, is still computationally challenging, especially if the data are high-dimensional. In this study we introduce a framework for constructing causal graphs from high-dimensional time series, whose computational cost scales linearly with the number of variables. The approach is based on the automatic identification of dynamical communities, groups of variables which mutually influence each other and can therefore be described as a single node in a causal graph. These communities are efficiently identified by optimizing the Information Imbalance, a statistical quantity that assigns a weight to each putative causal variable based on its information content relative to a target variable. The communities are then ordered starting from the fully autonomous ones, whose evolution is independent from all the others, to those that are progressively dependent on other communities, building in this manner a community causal graph. We demonstrate the computational efficiency and the accuracy of our approach on time-discrete and time-continuous dynamical systems including up to 80 variables. |
| 20 | Semiparametric Double Reinforcement Learning with Applications to Long-Term Causal Inference | 2025-01-12 | 展开Long-term causal effects often must be estimated from short-term data due to limited follow-up in healthcare, economics, and online platforms. Markov Decision Processes (MDPs) provide a natural framework for capturing such long-term dynamics through sequences of states, actions, and rewards. Double Reinforcement Learning (DRL) enables efficient inference on policy values in MDPs, but nonparametric implementations require strong intertemporal overlap assumptions and often exhibit high variance and instability. We propose a semiparametric extension of DRL for efficient inference on linear functionals of the Q-function--such as policy values--in infinite-horizon, time-homogeneous MDPs. By imposing structural restrictions on the Q-function, our approach relaxes the strong overlap conditions required by nonparametric methods and improves statistical efficiency. Under model misspecification, our estimators target the functional of the best-approximating Q-function, with only second-order bias. We provide conditions for valid inference using sieve methods and data-driven model selection. A central challenge in DRL is the estimation of nuisance functions, such as density ratios, which often involve difficult minimax optimization. To address this, we introduce a novel plug-in estimator based on isotonic Bellman calibration, which combines fitted Q-iteration with an isotonic regression adjustment. The estimator is debiased without requiring estimation of additional nuisance functions and reduces high-dimensional overlap assumptions to a one-dimensional condition. Bellman calibration extends isotonic calibration--widely used in prediction and classification--to the MDP setting and may be of independent interest. |
| 21 | CauSkelNet: Causal Representation Learning for Human Behaviour Analysis | 2024-09-23 | 展开Traditional machine learning methods for movement recognition often struggle with limited model interpretability and a lack of insight into human movement dynamics. This study introduces a novel representation learning framework based on causal inference to address these challenges. Our two-stage approach combines the Peter-Clark (PC) algorithm and Kullback-Leibler (KL) divergence to identify and quantify causal relationships between human joints. By capturing joint interactions, the proposed causal Graph Convolutional Network (GCN) produces interpretable and robust representations. Experimental results on the EmoPain dataset demonstrate that the causal GCN outperforms traditional GCNs in accuracy, F1 score, and recall, particularly in detecting protective behaviors. This work contributes to advancing human motion analysis and lays a foundation for adaptive and intelligent healthcare solutions. |
| 22 | Empirical evidence of Large Language Model's influence on human spoken communication | 2024-09-03 | 展开From the invention of writing and the printing press, to television and social media, human history is punctuated by major innovations in communication technology, which fundamentally altered how ideas spread and reshaped our culture. Recent chatbots powered by generative artificial intelligence constitute a novel medium that encodes cultural patterns in their neural representations and disseminates them in conversations with hundreds of millions of people. Understanding whether these patterns transmit into human language, and ultimately shape human culture, is a fundamental question. While fully quantifying the causal impact of a chatbot like ChatGPT on human culture is very challenging, lexicographic shift in human spoken communication may offer an early indicator of such broad phenomenon. Here, we apply econometric causal inference techniques to 740,249 hours of human discourse from 360,445 YouTube academic talks and 771,591 conversational podcast episodes across multiple disciplines. We detect a measurable and abrupt increase in the use of words preferentially generated by ChatGPT, such as delve, comprehend, boast, swift, and meticulous, after its release. These findings suggest a scenario where machines, originally trained on human data and subsequently exhibiting their own cultural traits, can, in turn, measurably reshape human culture. This marks the beginning of a closed cultural feedback loop in which cultural traits circulate bidirectionally between humans and machines. Our results motivate further research into the evolution of human-machine culture, and raise concerns over the erosion of linguistic and cultural diversity, and the risks of scalable manipulation. |
| 23 | A General Framework on Conditions for Constraint-based Causal Learning | 2024-08-14 | 展开Most constraint-based causal learning algorithms provably return the correct causal graph under certain correctness conditions, such as faithfulness. By representing any constraint-based causal learning algorithm using the notion of a property, we provide a general framework to obtain and study correctness conditions for these algorithms. From the framework, we provide exact correctness conditions for the PC algorithm, which are then related to the correctness conditions of some other existing causal discovery algorithms. The framework also suggests a paradigm for designing causal learning algorithms which allows for the correctness conditions of algorithms to be controlled for before designing the actual algorithm, and has the following implications. We show that the sparsest Markov representation condition is the weakest correctness condition for algorithms that output ancestral graphs or directed acyclic graphs satisfying any existing notions of minimality. We also reason that Pearl-minimality is necessary for meaningful causal learning but not sufficient to relax the faithfulness condition and, as such, has to be strengthened, such as by including background knowledge, for causal learning beyond faithfulness. |
| 24 | Quantification and cross-fitting inference of asymmetric relations under generative exposure mapping models | 2023-11-08 | 展开Learning directionality between variables is crucial yet challenging, especially for mechanistic relationships without a priori ordering assumptions. We propose a coefficient of asymmetry to quantify directional asymmetry using Shannon's entropy within a generative exposure mapping (GEM) framework. GEMs arise from experiments where a generative function |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | TurboVSR: Fantastic Video Upscalers and Where to Find Them | 2025-06-30 | 展开Diffusion-based generative models have demonstrated exceptional promise in the video super-resolution (VSR) task, achieving a substantial advancement in detail generation relative to prior methods. However, these approaches face significant computational efficiency challenges. For instance, current techniques may require tens of minutes to super-resolve a mere 2-second, 1080p video. In this paper, we present TurboVSR, an ultra-efficient diffusion-based video super-resolution model. Our core design comprises three key aspects: (1) We employ an autoencoder with a high compression ratio of 32$\times$32$\times$8 to reduce the number of tokens. (2) Highly compressed latents pose substantial challenges for training. We introduce factorized conditioning to mitigate the learning complexity: we first learn to super-resolve the initial frame; subsequently, we condition the super-resolution of the remaining frames on the high-resolution initial frame and the low-resolution subsequent frames. (3) We convert the pre-trained diffusion model to a shortcut model to enable fewer sampling steps, further accelerating inference. As a result, TurboVSR performs on par with state-of-the-art VSR methods, while being 100+ times faster, taking only 7 seconds to process a 2-second long 1080p video. TurboVSR also supports image resolution by considering image as a one-frame video. Our efficient design makes SR beyond 1080p possible, results on 4K (3648$\times$2048) image SR show surprising fine details. |
| 2 | VSRM: A Robust Mamba-Based Framework for Video Super-Resolution | 2025-06-28 | 展开Video super-resolution remains a major challenge in low-level vision tasks. To date, CNN- and Transformer-based methods have delivered impressive results. However, CNNs are limited by local receptive fields, while Transformers struggle with quadratic complexity, posing challenges for processing long sequences in VSR. Recently, Mamba has drawn attention for its long-sequence modeling, linear complexity, and large receptive fields. In this work, we propose VSRM, a novel \textbf{V}ideo \textbf{S}uper-\textbf{R}esolution framework that leverages the power of \textbf{M}amba. VSRM introduces Spatial-to-Temporal Mamba and Temporal-to-Spatial Mamba blocks to extract long-range spatio-temporal features and enhance receptive fields efficiently. To better align adjacent frames, we propose Deformable Cross-Mamba Alignment module. This module utilizes a deformable cross-mamba mechanism to make the compensation stage more dynamic and flexible, preventing feature distortions. Finally, we minimize the frequency domain gaps between reconstructed and ground-truth frames by proposing a simple yet effective Frequency Charbonnier-like loss that better preserves high-frequency content and enhances visual quality. Through extensive experiments, VSRM achieves state-of-the-art results on diverse benchmarks, establishing itself as a solid foundation for future research. |
| 3 | SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution | 2025-06-24 | 展开Latent diffusion models have emerged as a leading paradigm for efficient video generation. However, as user expectations shift toward higher-resolution outputs, relying solely on latent computation becomes inadequate. A promising approach involves decoupling the process into two stages: semantic content generation and detail synthesis. The former employs a computationally intensive base model at lower resolutions, while the latter leverages a lightweight cascaded video super-resolution (VSR) model to achieve high-resolution output. In this work, we focus on studying key design principles for latter cascaded VSR models, which are underexplored currently. First, we propose two degradation strategies to generate training pairs that better mimic the output characteristics of the base model, ensuring alignment between the VSR model and its upstream generator. Second, we provide critical insights into VSR model behavior through systematic analysis of (1) timestep sampling strategies, (2) noise augmentation effects on low-resolution (LR) inputs. These findings directly inform our architectural and training innovations. Finally, we introduce interleaving temporal unit and sparse local attention to achieve efficient training and inference, drastically reducing computational overhead. Extensive experiments demonstrate the superiority of our framework over existing methods, with ablation studies confirming the efficacy of each design choice. Our work establishes a simple yet effective baseline for cascaded video super-resolution generation, offering practical insights to guide future advancements in efficient cascaded synthesis systems. |
| 4 | One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution | 2025-06-18 | 展开It is a challenging problem to reproduce rich spatial details while maintaining temporal consistency in real-world video super-resolution (Real-VSR), especially when we leverage pre-trained generative models such as stable diffusion (SD) for realistic details synthesis. Existing SD-based Real-VSR methods often compromise spatial details for temporal coherence, resulting in suboptimal visual quality. We argue that the key lies in how to effectively extract the degradation-robust temporal consistency priors from the low-quality (LQ) input video and enhance the video details while maintaining the extracted consistency priors. To achieve this, we propose a Dual LoRA Learning (DLoRAL) paradigm to train an effective SD-based one-step diffusion model, achieving realistic frame details and temporal consistency simultaneously. Specifically, we introduce a Cross-Frame Retrieval (CFR) module to aggregate complementary information across frames, and train a Consistency-LoRA (C-LoRA) to learn robust temporal representations from degraded inputs. After consistency learning, we fix the CFR and C-LoRA modules and train a Detail-LoRA (D-LoRA) to enhance spatial details while aligning with the temporal space defined by C-LoRA to keep temporal coherence. The two phases alternate iteratively for optimization, collaboratively delivering consistent and detail-rich outputs. During inference, the two LoRA branches are merged into the SD model, allowing efficient and high-quality video restoration in a single diffusion step. Experiments show that DLoRAL achieves strong performance in both accuracy and speed. Code and models are available at https://github.com/yjsunnn/DLoRAL. |
| 5 | Super-Resolution Generative Adversarial Networks based Video Enhancement | 2025-05-14 | 展开This study introduces an enhanced approach to video super-resolution by extending ordinary Single-Image Super-Resolution (SISR) Super-Resolution Generative Adversarial Network (SRGAN) structure to handle spatio-temporal data. While SRGAN has proven effective for single-image enhancement, its design does not account for the temporal continuity required in video processing. To address this, a modified framework that incorporates 3D Non-Local Blocks is proposed, which is enabling the model to capture relationships across both spatial and temporal dimensions. An experimental training pipeline is developed, based on patch-wise learning and advanced data degradation techniques, to simulate real-world video conditions and learn from both local and global structures and details. This helps the model generalize better and maintain stability across varying video content while maintaining the general structure besides the pixel-wise correctness. Two model variants-one larger and one more lightweight-are presented to explore the trade-offs between performance and efficiency. The results demonstrate improved temporal coherence, sharper textures, and fewer visual artifacts compared to traditional single-image methods. This work contributes to the development of practical, learning-based solutions for video enhancement tasks, with potential applications in streaming, gaming, and digital restoration. |
| 6 | Spatial Degradation-Aware and Temporal Consistent Diffusion Model for Compressed Video Super-Resolution | 2025-02-11 | 展开Due to storage and bandwidth limitations, videos transmitted over the Internet often exhibit low quality, characterized by low-resolution and compression artifacts. Although video super-resolution (VSR) is an efficient video enhancing technique, existing VSR methods focus less on compressed videos. Consequently, directly applying general VSR approaches fails to improve practical videos with compression artifacts, especially when frames are highly compressed at a low bit rate. The inevitable quantization information loss complicates the reconstruction of texture details. Recently, diffusion models have shown superior performance in low-level visual tasks. Leveraging the high-realism generation capability of diffusion models, we propose a novel method that exploits the priors of pre-trained diffusion models for compressed VSR. To mitigate spatial distortions and refine temporal consistency, we introduce a Spatial Degradation-Aware and Temporal Consistent (SDATC) diffusion model. Specifically, we incorporate a distortion control module (DCM) to modulate diffusion model inputs, thereby minimizing the impact of noise from low-quality frames on the generation stage. Subsequently, the diffusion model performs a denoising process to generate details, guided by a fine-tuned compression-aware prompt module (CAPM) and a spatio-temporal attention module (STAM). CAPM dynamically encodes compression-related information into prompts, enabling the sampling process to adapt to different degradation levels. Meanwhile, STAM extends the spatial attention mechanism into the spatio-temporal dimension, effectively capturing temporal correlations. Additionally, we utilize optical flow-based alignment during each denoising step to enhance the smoothness of output videos. Extensive experimental results on benchmark datasets demonstrate the effectiveness of our proposed modules in restoring compressed videos. |
| 7 | Low-Resource Video Super-Resolution using Memory, Wavelets, and Deformable Convolutions | 2025-02-03 | 展开The tradeoff between reconstruction quality and compute required for video super-resolution (VSR) remains a formidable challenge in its adoption for deployment on resource-constrained edge devices. While transformer-based VSR models have set new benchmarks for reconstruction quality in recent years, these require substantial computational resources. On the other hand, lightweight models that have been introduced even recently struggle to deliver state-of-the-art reconstruction. We propose a novel lightweight and parameter-efficient neural architecture for VSR that achieves state-of-the-art reconstruction accuracy with just 2.3 million parameters. Our model enhances information utilization based on several architectural attributes. Firstly, it uses 2D wavelet decompositions strategically interlayered with learnable convolutional layers to utilize the inductive prior of spatial sparsity of edges in visual data. Secondly, it uses a single memory tensor to capture inter-frame temporal information while avoiding the computational cost of previous memory-based schemes. Thirdly, it uses residual deformable convolutions for implicit inter-frame object alignment that improve upon deformable convolutions by enhancing spatial information in inter-frame feature differences. Architectural insights from our model can pave the way for real-time VSR on the edge, such as display devices for streaming data. |
| 8 | RefVSR++: Exploiting Reference Inputs for Reference-based Video Super-resolution | 2023-07-06 | 展开Smartphones with multi-camera systems, featuring cameras with varying field-of-views (FoVs), are increasingly common. This variation in FoVs results in content differences across videos, paving the way for an innovative approach to video super-resolution (VSR). This method enhances the VSR performance of lower resolution (LR) videos by leveraging higher resolution reference (Ref) videos. Previous works, which operate on this principle, generally expand on traditional VSR models by combining LR and Ref inputs over time into a unified stream. However, we can expect that better results are obtained by independently aggregating these Ref image sequences temporally. Therefore, we introduce an improved method, RefVSR++, which performs the parallel aggregation of LR and Ref images in the temporal direction, aiming to optimize the use of the available data. RefVSR++ also incorporates improved mechanisms for aligning image features over time, crucial for effective VSR. Our experiments demonstrate that RefVSR++ outperforms previous works by over 1dB in PSNR, setting a new benchmark in the field. |
7. knowledge graph/knowledge distillation/knowledge representation/knowledge transfer/knowledge embedding
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | The Trilemma of Truth in Large Language Models | 2025-06-30 | 展开We often attribute human characteristics to large language models (LLMs) and claim that they "know" certain things. LLMs have an internal probabilistic knowledge that represents information retained during training. How can we assess the veracity of this knowledge? We examine two common methods for probing the veracity of LLMs and discover several assumptions that are flawed. To address these flawed assumptions, we introduce sAwMIL (short for Sparse Aware Multiple-Instance Learning), a probing method that utilizes the internal activations of LLMs to separate statements into true, false, and neither. sAwMIL is based on multiple-instance learning and conformal prediction. We evaluate sAwMIL on 5 validity criteria across 16 open-source LLMs, including both default and chat-based variants, as well as on 3 new datasets. Among the insights we provide are: (1) the veracity signal is often concentrated in the third quarter of an LLM's depth; (2) truth and falsehood signals are not always symmetric; (3) linear probes perform better on chat models than on default models; (4) nonlinear probes may be required to capture veracity signals for some LLMs with reinforcement learning from human feedback or knowledge distillation; and (5) LLMs capture a third type of signal that is distinct from true and false and is neither true nor false. These findings provide a reliable method for verifying what LLMs "know" and how certain they are of their probabilistic internal knowledge. |
| 2 | Efficient Interleaved Speech Modeling through Knowledge Distillation | 2025-06-30 | 展开Current speech language models exceed the size and latency constraints of many deployment environments. We build compact, expressive speech generation models through layer-aligned distillation, matching hidden states, attention maps, and softened logits to compress large multimodal transformers by 3x with minimal loss in performance. We introduce TinyWave, a family of 2B-parameter models for speech-to-speech and interleaved speech-text generation, trained on 50,000 hours of public audio. TinyWave supports (i) speech-only generation using phonetic or expressive tokens and (ii) mixed speech-text continuations. Evaluation on Libri-Light shows TinyWave within 1.4 normalized perplexity points of its teacher. Accuracy on spoken StoryCloze and SALMon reaches 93-97% of the teacher's performance, outperforming size-matched baselines. These models are optimized for deployment on commodity hardware, enabling applications in real-time conversational agents, assistive technologies, and low-resource environments. We release models, training code, and evaluation scripts to support reproducible research on compact, expressive speech generation. |
| 3 | When Test-Time Adaptation Meets Self-Supervised Models | 2025-06-30 | 展开Training on test-time data enables deep learning models to adapt to dynamic environmental changes, enhancing their practical applicability. Online adaptation from source to target domains is promising but it remains highly reliant on the performance of source pretrained model. In this paper, we investigate whether test-time adaptation (TTA) methods can continuously improve models trained via self-supervised learning (SSL) without relying on source pretraining. We introduce a self-supervised TTA protocol after observing that existing TTA approaches struggle when directly applied to self-supervised models with low accuracy on the source domain. Furthermore, we propose a collaborative learning framework that integrates SSL and TTA models, leveraging contrastive learning and knowledge distillation for stepwise representation refinement. We validate our method on diverse self-supervised models, including DINO, MoCo, and iBOT, across TTA benchmarks. Extensive experiments validate the effectiveness of our approach in SSL, showing that it achieves competitive performance even without source pretraining. |
| 4 | Competitive Distillation: A Simple Learning Strategy for Improving Visual Classification | 2025-06-29 | 展开Deep Neural Networks (DNNs) have significantly advanced the field of computer vision. To improve DNN training process, knowledge distillation methods demonstrate their effectiveness in accelerating network training by introducing a fixed learning direction from the teacher network to student networks. In this context, several distillation-based optimization strategies are proposed, e.g., deep mutual learning and self-distillation, as an attempt to achieve generic training performance enhancement through the cooperative training of multiple networks. However, such strategies achieve limited improvements due to the poor understanding of the impact of learning directions among networks across different iterations. In this paper, we propose a novel competitive distillation strategy that allows each network in a group to potentially act as a teacher based on its performance, enhancing the overall learning performance. Competitive distillation organizes a group of networks to perform a shared task and engage in competition, where competitive optimization is proposed to improve the parameter updating process. We further introduce stochastic perturbation in competitive distillation, aiming to motivate networks to induce mutations to achieve better visual representations and global optimum. The experimental results show that competitive distillation achieves promising performance in diverse tasks and datasets. |
| 5 | Context-Driven Knowledge Graph Completion with Semantic-Aware Relational Message Passing | 2025-06-29 | 展开Semantic context surrounding a triplet |
| 6 | Flow-Modulated Scoring for Semantic-Aware Knowledge Graph Completion | 2025-06-29 | 展开Effective modeling of multifaceted relations is pivotal for Knowledge Graph Completion (KGC). However, a majority of existing approaches are predicated on static, embedding-based scoring, exhibiting inherent limitations in capturing contextual dependencies and relational dynamics. Addressing this gap, we propose the Flow-Modulated Scoring (FMS) framework. FMS comprises two principal components: (1) a semantic context learning module that encodes context-sensitive entity representations, and (2) a conditional flow-matching module designed to learn the dynamic transformation from a head to a tail embedding, governed by the aforementioned context. The resultant predictive vector field, representing the context-informed relational path, serves to dynamically refine the initial static score of an entity pair. Through this synergy of context-aware static representations and conditioned dynamic information, FMS facilitates a more profound modeling of relational semantics. Comprehensive evaluations on several standard benchmarks demonstrate that our proposed method surpasses prior state-of-the-art results. |
| 7 | ReMem: Mutual Information-Aware Fine-tuning of Pretrained Vision Transformers for Effective Knowledge Distillation | 2025-06-29 | 展开Knowledge distillation from pretrained visual representation models offers an effective approach to improve small, task-specific production models. However, the effectiveness of such knowledge transfer drops significantly when distilling from strong models that are pretrained in a large scale. In this paper, we address this challenge for pretrained Vision Transformers (ViTs) by exploring methods to fine-tune them for more effective knowledge transfer. Motivated by the connection between mutual information and distillation effectiveness, we propose to employ mutual information-aware optimization during finetuning. For small or highly-imbalanced downstream datasets where such optimization becomes less effective, we introduce a simple yet effective heuristic of reweighting MLP blocks. This approach is inspired by our observation that top MLP blocks are primarily responsible for mutual information loss. Our method enables small student models to benefit from those pretrained models among the strongest. |
| 8 | Beyond Code: The Multidimensional Impacts of Large Language Models in Software Development | 2025-06-28 | 展开Large language models (LLMs) are poised to significantly impact software development, especially in the Open-Source Software (OSS) sector. To understand this impact, we first outline the mechanisms through which LLMs may influence OSS through code development, collaborative knowledge transfer, and skill development. We then empirically examine how LLMs affect OSS developers' work in these three key areas. Leveraging a natural experiment from a temporary ChatGPT ban in Italy, we employ a Difference-in-Differences framework with two-way fixed effects to analyze data from all OSS developers on GitHub in three similar countries, Italy, France, and Portugal, totaling 88,022 users. We find that access to ChatGPT increases developer productivity by 6.4%, knowledge sharing by 9.6%, and skill acquisition by 8.4%. These benefits vary significantly by user experience level: novice developers primarily experience productivity gains, whereas more experienced developers benefit more from improved knowledge sharing and accelerated skill acquisition. In addition, we find that LLM-assisted learning is highly context-dependent, with the greatest benefits observed in technically complex, fragmented, or rapidly evolving contexts. We show that the productivity effects of LLMs extend beyond direct code generation to include enhanced collaborative learning and knowledge exchange among developers; dynamics that are essential for gaining a holistic understanding of LLMs' impact in OSS. Our findings offer critical managerial implications: strategically deploying LLMs can accelerate novice developers' onboarding and productivity, empower intermediate developers to foster knowledge sharing and collaboration, and support rapid skill acquisition, together enhancing long-term organizational productivity and agility. |
| 9 | Partial CLIP is Enough: Chimera-Seg for Zero-shot Semantic Segmentation | 2025-06-27 | 展开Zero-shot Semantic Segmentation (ZSS) aims to segment both seen and unseen classes using supervision from only seen classes. Beyond adaptation-based methods, distillation-based approaches transfer vision-language alignment of vision-language model, e.g., CLIP, to segmentation models. However, such knowledge transfer remains challenging due to: (1) the difficulty of aligning vision-based features with the textual space, which requires combining spatial precision with vision-language alignment; and (2) the semantic gap between CLIP's global representations and the local, fine-grained features of segmentation models. To address challenge (1), we propose Chimera-Seg, which integrates a segmentation backbone as the body and a CLIP-based semantic head as the head, like the Chimera in Greek mythology, combining spatial precision with vision-language alignment. Specifically, Chimera-Seg comprises a trainable segmentation model and a CLIP Semantic Head (CSH), which maps dense features into the CLIP-aligned space. The CSH incorporates a frozen subnetwork and fixed projection layers from the CLIP visual encoder, along with lightweight trainable components. The partial module from CLIP visual encoder, paired with the segmentation model, retains segmentation capability while easing the mapping to CLIP's semantic space. To address challenge (2), we propose Selective Global Distillation (SGD), which distills knowledge from dense features exhibiting high similarity to the CLIP CLS token, while gradually reducing the number of features used for alignment as training progresses. Besides, we also use a Semantic Alignment Module (SAM) to further align dense visual features with semantic embeddings extracted from the frozen CLIP text encoder. Experiments on two benchmarks show improvements of 0.9% and 1.2% in hIoU. |
| 10 | Seismic resolution enhancement via deep Learning with Knowledge Distillation and Domain Adaptation | 2025-06-27 | 展开High-resolution processing of seismic signals is crucial for subsurface geological characterization and thin-layer reservoir identification. Traditional high-resolution algorithms can partially recover high-frequency information but often lack robustness, computational efficiency, and consideration of inter-trace structural relationships. Many deep learning methods use end-to-end architectures that do not incorporate prior knowledge or address data domain disparities, leading to limited generalization.To overcome these challenges, this paper presents the Domain-Adaptive Knowledge Distillation Network (DAKD-Net), which integrates a knowledge distillation strategy with a domain adaptation mechanism for high-resolution seismic data processing. Trained on datasets from forward modeling, DAKD-Net establishes physical relationships between low and high-resolution data, extracting high-frequency prior knowledge during a guided phase before detail restoration without prior conditions. Domain adaptation enhances the model's generalization to real seismic data, improving both generalization capability and structural expression accuracy.DAKD-Net employs a U-Net backbone to extract spatial structural information from multi-trace seismic profiles. The knowledge distillation mechanism enables prior knowledge transfer, allowing recovery of high-resolution data directly from low-resolution inputs. Domain-adaptive fine-tuning further enhances the network's performance in actual survey areas. Experimental results show that DAKD-Net outperforms traditional methods and classical deep networks in longitudinal resolution and complex structural detail restoration, demonstrating strong robustness and practicality. |
| 11 | Shifting Narratives: A Longitudinal Analysis of Media Trends and Public Attitudes on Homelessness | 2025-06-26 | 展开Within the field of media framing, homelessness has been a historically under-researched topic. Framing theory states that the media's method of presenting information plays a pivotal role in controlling public sentiment toward a topic. The sentiment held towards homeless individuals influences their ability to access jobs, housing, and resources as a result of discrimination. This study analyzes the topic and sentiment trends in related media articles to validate framing theory within the scope of homelessness. It correlates these shifts in media reporting with public sentiment. We examine state-level trends in California, Florida, Washington, Oregon, and New York from 2015 to 2023. We utilize the GDELT 2.0 Global Knowledge Graph (GKG) database to gather article data and use X to measure public sentiment towards homeless individuals. Additionally, to identify if there is a correlation between media reporting and public policy, we examine the media's impact on state-level legislation. Our research uses Granger-causality tests and vector autoregressive (VAR) models to establish a correlation between media framing and public sentiment. We also use latent Dirichlet allocation (LDA) and GPT-3.5 (LLM-as-annotator paradigm) for topic modeling and sentiment analysis. Our findings demonstrate a statistically significant correlation between media framing and public sentiment, especially in states with high homelessness rates. We found no significant correlation between media framing and legislation, suggesting a possible disconnect between public opinion and policy-making. These findings reveal the broader impact of the media's framing decisions and delineate its ability to affect society. |
| 12 | Unveiling Causal Reasoning in Large Language Models: Reality or Mirage? | 2025-06-26 | 展开Causal reasoning capability is critical in advancing large language models (LLMs) toward strong artificial intelligence. While versatile LLMs appear to have demonstrated capabilities in understanding contextual causality and providing responses that obey the laws of causality, it remains unclear whether they perform genuine causal reasoning akin to humans. However, current evidence indicates the contrary. Specifically, LLMs are only capable of performing shallow (level-1) causal reasoning, primarily attributed to the causal knowledge embedded in their parameters, but they lack the capacity for genuine human-like (level-2) causal reasoning. To support this hypothesis, methodologically, we delve into the autoregression mechanism of transformer-based LLMs, revealing that it is not inherently causal. Empirically, we introduce a new causal Q&A benchmark called CausalProbe-2024, whose corpora are fresh and nearly unseen for the studied LLMs. The LLMs exhibit a significant performance drop on CausalProbe-2024 compared to earlier benchmarks, indicating the fact that they primarily engage in level-1 causal reasoning. To bridge the gap towards level-2 causal reasoning, we draw inspiration from the fact that human reasoning is usually facilitated by general knowledge and intended goals. We propose G^2-Reasoner, a method that incorporates general knowledge and goal-oriented prompts into LLMs' causal reasoning processes. Experiments demonstrate that G^2-Reasoner significantly enhances LLMs' causal reasoning capability, particularly in fresh and counterfactual contexts. This work sheds light on a new path for LLMs to advance towards genuine causal reasoning, going beyond level-1 and making strides towards level-2. |
| 13 | Condensed Representation of RDF and its Application on Graph Versioning | 2025-06-26 | 展开The study of the evolving phenomena in a domain helps to understand the relationships between entities at different points in time and predict future trends. These phenomena, often complex, can be represented using knowledge graphs, which have the capability to model heterogeneous data from multiple sources. Nowadays, a considerable amount of sources delivering periodic updates to knowledge graphs in various domains is openly available. The evolution of data is of interest to knowledge graph management systems, and therefore it is crucial to organize these constantly evolving data to make them easily accessible and exploitable for analyzes. In this article, we will present and formalize the condensed representation of these evolving graphs. |
| 14 | Distilling Normalizing Flows | 2025-06-26 | 展开Explicit density learners are becoming an increasingly popular technique for generative models because of their ability to better model probability distributions. They have advantages over Generative Adversarial Networks due to their ability to perform density estimation and having exact latent-variable inference. This has many advantages, including: being able to simply interpolate, calculate sample likelihood, and analyze the probability distribution. The downside of these models is that they are often more difficult to train and have lower sampling quality. Normalizing flows are explicit density models, that use composable bijective functions to turn an intractable probability function into a tractable one. In this work, we present novel knowledge distillation techniques to increase sampling quality and density estimation of smaller student normalizing flows. We seek to study the capacity of knowledge distillation in Compositional Normalizing Flows to understand the benefits and weaknesses provided by these architectures. Normalizing flows have unique properties that allow for a non-traditional forms of knowledge transfer, where we can transfer that knowledge within intermediate layers. We find that through this distillation, we can make students significantly smaller while making substantial performance gains over a non-distilled student. With smaller models there is a proportionally increased throughput as this is dependent upon the number of bijectors, and thus parameters, in the network. |
| 15 | Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning | 2025-06-26 | 展开Foundation models have achieved great success in natural language processing (NLP) and computer vision (CV). Their success largely stems from the ability to integrate multi-domain knowledge in pre-training and transfer it to target domains. Considering graph data, especially graphs without textual features, is ubiquitous in real-world applications such as social networks and recommendation systems, some researchers have attempted to extend this paradigm to the graph field, aiming to construct graph foundation models. However, unlike CV and NLP, there are huge gaps among the semantics and properties of graphs in different domains, while current works still adopt traditional contrastive pre-training strategies designed in the single-domain scenario, which regard contrastive samples from different domains as equivalent. From experimental investigations, we discovered that inherent domain-specific differences prevent these strategies from effectively absorbing knowledge from different domains to generate informative representations. In this paper, we propose a novel multi-domain pre-training and cross-domain transfer framework, namely MDGCL.In the pre-training stage, we design a contrastive learning strategy to substantially recognize and capture domain differences, and introduce domain tokens to encode domain-level global information. In the downstream stage, we introduce a domain attention mechanism to enable fine-grained domain knowledge transfer. Extensive experiments on five benchmark datasets have demonstrated that our method outperforms state-of-the-art significantly, with the maximum improvement of 19.33% on accuracy and 19.13% on Macro-F1 score. |
| 16 | The role of preprints in open science: Accelerating knowledge transfer from science to technology | 2025-06-25 | 展开Preprints have become increasingly essential in the landscape of open science, facilitating not only the exchange of knowledge within the scientific community but also bridging the gap between science and technology. However, the impact of preprints on technological innovation, given their unreviewed nature, remains unclear. This study fills this gap by conducting a comprehensive scientometric analysis of patent citations to bioRxiv preprints submitted between 2013 and 2021, measuring and accessing the contribution of preprints in accelerating knowledge transfer from science to technology. Our findings reveal a growing trend of patent citations to bioRxiv preprints, with a notable surge in 2020, primarily driven by the COVID-19 pandemic. Preprints play a critical role in accelerating innovation, not only expedite the dissemination of scientific knowledge into technological innovation but also enhance the visibility of early research results in the patenting process, while journals remain essential for academic rigor and reliability. The substantial number of post-online-publication patent citations highlights the critical role of the open science model-particularly the "open access" effect of preprints-in amplifying the impact of science on technological innovation. This study provides empirical evidence that open science policies encouraging the early sharing of research outputs, such as preprints, contribute to more efficient linkage between science and technology, suggesting an acceleration in the pace of innovation, higher innovation quality, and economic benefits. |
| 17 | KnowMap: Efficient Knowledge-Driven Task Adaptation for LLMs | 2025-06-24 | 展开While Large Language Models (LLMs) possess significant capabilities in open-world agent tasks, they also face challenges in rapidly adapting to new, specialized tasks due to their reliance on static pre-trained knowledge. Traditional methods such as fine-tuning are often costly, data-intensive, and may lead to "catastrophic forgetting." Therefore, we present KnowMap, a novel approach that dynamically constructs a knowledge base from environmental and experiential data. KnowMap fine-tunes a small knowledge-embedding model to equip a larger LLM with valuable task-specific knowledge. Our experiments on the ScienceWorld benchmark demonstrate 17.71% improvement for the performance of gpt-4-turbo model. KnowMap not only provides an efficient and effective means for LLM task-adapting, but also highlights how integrating environmental and experiential knowledge can enhance LLMs' reasoning capabilities. |
| 18 | Generalizing vision-language models to novel domains: A comprehensive survey | 2025-06-23 | 展开Recently, vision-language pretraining has emerged as a transformative technique that integrates the strengths of both visual and textual modalities, resulting in powerful vision-language models (VLMs). Leveraging web-scale pretraining data, these models exhibit strong zero-shot capabilities. However, their performance often deteriorates when confronted with domain-specific or specialized generalization tasks. To address this, a growing body of research focuses on transferring or generalizing the rich knowledge embedded in VLMs to various downstream applications. This survey aims to comprehensively summarize the generalization settings, methodologies, benchmarking and results in VLM literatures. Delving into the typical VLM structures, current literatures are categorized into prompt-based, parameter-based and feature-based methods according to the transferred modules. The differences and characteristics in each category are furthered summarized and discussed by revisiting the typical transfer learning (TL) settings, providing novel interpretations for TL in the era of VLMs. Popular benchmarks for VLM generalization are further introduced with thorough performance comparisons among the reviewed methods. Following the advances in large-scale generalizable pretraining, this survey also discusses the relations and differences between VLMs and up-to-date multimodal large language models (MLLM), e.g., DeepSeek-VL. By systematically reviewing the surging literatures in vision-language research from a novel and practical generalization prospective, this survey contributes to a clear landscape of current and future multimodal researches. |
| 19 | Dual-Forward Path Teacher Knowledge Distillation: Bridging the Capacity Gap Between Teacher and Student | 2025-06-23 | 展开Knowledge distillation (KD) provides an effective way to improve the performance of a student network under the guidance of pre-trained teachers. However, this approach usually brings in a large capacity gap between teacher and student networks, limiting the distillation gains. Previous methods addressing this problem either discard accurate knowledge representation or fail to dynamically adjust the transferred knowledge, which is less effective in addressing the capacity gap problem and hinders students from achieving comparable performance with the pre-trained teacher. In this work, we extend the ideology of prompt-based learning to address the capacity gap problem, and propose Dual-Forward Path Teacher Knowledge Distillation (DFPT-KD), which replaces the pre-trained teacher with a novel dual-forward path teacher to supervise the learning of student. The key to DFPT-KD is prompt-based tuning, i.e., establishing an additional prompt-based forward path within the pre-trained teacher and optimizing it with the pre-trained teacher frozen to make the transferred knowledge compatible with the representation ability of the student. Extensive experiments demonstrate that DFPT-KD leads to trained students performing better than the vanilla KD. To make the transferred knowledge better compatible with the representation abilities of the student, we further fine-tune the whole prompt-based forward path, yielding a novel distillation approach dubbed DFPT-KD+. By extensive experiments, it is shown that DFPT-KD+ improves upon DFPT-KD and achieves state-of-the-art accuracy performance. |
| 20 | Action Language BC+ | 2025-06-22 | 展开Action languages are formal models of parts of natural language that are designed to describe effects of actions. Many of these languages can be viewed as high level notations of answer set programs structured to represent transition systems. However, the form of answer set programs considered in the earlier work is quite limited in comparison with the modern Answer Set Programming (ASP) language, which allows several useful constructs for knowledge representation, such as choice rules, aggregates, and abstract constraint atoms. We propose a new action language called BC+, which closes the gap between action languages and the modern ASP language. The main idea is to define the semantics of BC+ in terms of general stable model semantics for propositional formulas, under which many modern ASP language constructs can be identified with shorthands for propositional formulas. Language BC+ turns out to be sufficiently expressive to encompass the best features of other action languages, such as languages B, C, C+, and BC. Computational methods available in ASP solvers are readily applicable to compute BC+, which led to an implementation of the language by extending system cplus2asp. |
| 21 | A Community-driven vision for a new Knowledge Resource for AI | 2025-06-19 | 展开The long-standing goal of creating a comprehensive, multi-purpose knowledge resource, reminiscent of the 1984 Cyc project, still persists in AI. Despite the success of knowledge resources like WordNet, ConceptNet, Wolfram |
| 22 | Approximation Fixpoint Theory with Refined Approximation Spaces | 2025-06-19 | 展开Approximation Fixpoint Theory (AFT) is a powerful theory covering various semantics of non-monotonic reasoning formalisms in knowledge representation such as Logic Programming and Answer Set Programming. Many semantics of such non-monotonic formalisms can be characterized as suitable fixpoints of a non-monotonic operator on a suitable lattice. Instead of working on the original lattice, AFT operates on intervals in such lattice to approximate or construct the fixpoints of interest. While AFT has been applied successfully across a broad range of non-monotonic reasoning formalisms, it is confronted by its limitations in other, relatively simple, examples. In this paper, we overcome those limitations by extending consistent AFT to deal with approximations that are more refined than intervals. Therefore, we introduce a more general notion of approximation spaces, showcase the improved expressiveness and investigate relations between different approximation spaces. |
| 23 | KG-FGNN: Knowledge-guided GNN Foundation Model for Fertilisation-oriented Soil GHG Flux Prediction | 2025-06-18 | 展开Precision soil greenhouse gas (GHG) flux prediction is essential in agricultural systems for assessing environmental impacts, developing emission mitigation strategies and promoting sustainable agriculture. Due to the lack of advanced sensor and network technologies on majority of farms, there are challenges in obtaining comprehensive and diverse agricultural data. As a result, the scarcity of agricultural data seriously obstructs the application of machine learning approaches in precision soil GHG flux prediction. This research proposes a knowledge-guided graph neural network framework that addresses the above challenges by integrating knowledge embedded in an agricultural process-based model and graph neural network techniques. Specifically, we utilise the agricultural process-based model to simulate and generate multi-dimensional agricultural datasets for 47 countries that cover a wide range of agricultural variables. To extract key agricultural features and integrate correlations among agricultural features in the prediction process, we propose a machine learning framework that integrates the autoencoder and multi-target multi-graph based graph neural networks, which utilises the autoencoder to selectively extract significant agricultural features from the agricultural process-based model simulation data and the graph neural network to integrate correlations among agricultural features for accurately predict fertilisation-oriented soil GHG fluxes. Comprehensive experiments were conducted with both the agricultural simulation dataset and real-world agricultural dataset to evaluate the proposed approach in comparison with well-known baseline and state-of-the-art regression methods. The results demonstrate that our proposed approach provides superior accuracy and stability in fertilisation-oriented soil GHG prediction. |
| 24 | RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills | 2025-06-17 | 展开Endowing robots with tool design abilities is critical for enabling them to solve complex manipulation tasks that would otherwise be intractable. While recent generative frameworks can automatically synthesize task settings, such as 3D scenes and reward functions, they have not yet addressed the challenge of tool-use scenarios. Simply retrieving human-designed tools might not be ideal since many tools (e.g., a rolling pin) are difficult for robotic manipulators to handle. Furthermore, existing tool design approaches either rely on predefined templates with limited parameter tuning or apply generic 3D generation methods that are not optimized for tool creation. To address these limitations, we propose RobotSmith, an automated pipeline that leverages the implicit physical knowledge embedded in vision-language models (VLMs) alongside the more accurate physics provided by physics simulations to design and use tools for robotic manipulation. Our system (1) iteratively proposes tool designs using collaborative VLM agents, (2) generates low-level robot trajectories for tool use, and (3) jointly optimizes tool geometry and usage for task performance. We evaluate our approach across a wide range of manipulation tasks involving rigid, deformable, and fluid objects. Experiments show that our method consistently outperforms strong baselines in terms of both task success rate and overall performance. Notably, our approach achieves a 50.0% average success rate, significantly surpassing other baselines such as 3D generation (21.4%) and tool retrieval (11.1%). Finally, we deploy our system in real-world settings, demonstrating that the generated tools and their usage plans transfer effectively to physical execution, validating the practicality and generalization capabilities of our approach. |
| 25 | Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models | 2025-06-17 | 展开Assistive teleoperation, where control is shared between a human and a robot, enables efficient and intuitive human-robot collaboration in diverse and unstructured environments. A central challenge in real-world assistive teleoperation is for the robot to infer a wide range of human intentions from user control inputs and to assist users with correct actions. Existing methods are either confined to simple, predefined scenarios or restricted to task-specific data distributions at training, limiting their support for real-world assistance. We introduce Casper, an assistive teleoperation system that leverages commonsense knowledge embedded in pre-trained visual language models (VLMs) for real-time intent inference and flexible skill execution. Casper incorporates an open-world perception module for a generalized understanding of novel objects and scenes, a VLM-powered intent inference mechanism that leverages commonsense reasoning to interpret snippets of teleoperated user input, and a skill library that expands the scope of prior assistive teleoperation systems to support diverse, long-horizon mobile manipulation tasks. Extensive empirical evaluation, including human studies and system ablations, demonstrates that Casper improves task performance, reduces human cognitive load, and achieves higher user satisfaction than direct teleoperation and assistive teleoperation baselines. |
| 26 | Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods | 2025-06-05 | 展开Real-world knowledge can take various forms, including structured, semi-structured, and unstructured data. Among these, knowledge graphs are a form of structured human knowledge that integrate heterogeneous data sources into structured representations but typically reduce complex n-ary relations to simple triples, thereby losing higher-order relational details. In contrast, hypergraphs naturally represent n-ary relations with hyperedges, which directly connect multiple entities together. Yet hypergraph representation learning often overlooks entity roles in hyperedges, limiting the finegrained semantic modelling. To address these issues, knowledge hypergraphs and hyper-relational knowledge graphs combine the advantages of knowledge graphs and hypergraphs to better capture the complex structures and role-specific semantics of real world knowledge. This survey provides a comprehensive review of methods handling n-ary relational data, covering both knowledge hypergraphs and hyper-relational knowledge graphs literatures. We propose a two-dimensional taxonomy: the first dimension categorises models based on their methodology, i.e., translation-based models, tensor factorisation-based models, deep neural network-based models, logic rules-based models, and hyperedge expansion-based models. The second dimension classifies models according to their awareness of entity roles and positions in n-ary relations, dividing them into aware-less, position-aware, and role-aware approaches. Finally, we discuss existing datasets, training settings and strategies, and outline open challenges to inspire future research. |
| 27 | Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking | 2025-04-04 | 展开We present a novel approach for training small language models for reasoning-intensive document ranking that combines knowledge distillation with reinforcement learning optimization. While existing methods often rely on expensive human annotations or large black-box language models, our methodology leverages web data and a teacher LLM to automatically generate high-quality training examples with relevance explanations. By framing document ranking as a reinforcement learning problem and incentivizing explicit reasoning capabilities, we train a compact 3B parameter language model that achieves state-of-the-art performance on the BRIGHT benchmark. Our model ranks third on the leaderboard while using substantially fewer parameters than other approaches, outperforming models that are over 20 times larger. Through extensive experiments, we demonstrate that generating explanations during inference, rather than directly predicting relevance scores, enables more effective reasoning with smaller language models. The self-supervised nature of our method offers a scalable and interpretable solution for modern information retrieval systems. |
| 28 | Mitigating Knowledge Discrepancies among Multiple Datasets for Task-agnostic Unified Face Alignment | 2025-03-28 | 展开Despite the similar structures of human faces, existing face alignment methods cannot learn unified knowledge from multiple datasets with different landmark annotations. The limited training samples in a single dataset commonly result in fragile robustness in this field. To mitigate knowledge discrepancies among different datasets and train a task-agnostic unified face alignment (TUFA) framework, this paper presents a strategy to unify knowledge from multiple datasets. Specifically, we calculate a mean face shape for each dataset. To explicitly align these mean shapes on an interpretable plane based on their semantics, each shape is then incorporated with a group of semantic alignment embeddings. The 2D coordinates of these aligned shapes can be viewed as the anchors of the plane. By encoding them into structure prompts and further regressing the corresponding facial landmarks using image features, a mapping from the plane to the target faces is finally established, which unifies the learning target of different datasets. Consequently, multiple datasets can be utilized to boost the generalization ability of the model. The successful mitigation of discrepancies also enhances the efficiency of knowledge transferring to a novel dataset, significantly boosts the performance of few-shot face alignment. Additionally, the interpretable plane endows TUFA with a task-agnostic characteristic, enabling it to locate landmarks unseen during training in a zero-shot manner. Extensive experiments are carried on seven benchmarks and the results demonstrate an impressive improvement in face alignment brought by knowledge discrepancies mitigation. The code is available at https://github.com/Jiahao-UTS/TUFA. |
| 29 | Agentic Medical Knowledge Graphs Enhance Medical Question Answering: Bridging the Gap Between LLMs and Evolving Medical Knowledge | 2025-02-18 | 展开Large Language Models (LLMs) have significantly advanced medical question-answering by leveraging extensive clinical data and medical literature. However, the rapid evolution of medical knowledge and the labor-intensive process of manually updating domain-specific resources pose challenges to the reliability of these systems. To address this, we introduce Agentic Medical Graph-RAG (AMG-RAG), a comprehensive framework that automates the construction and continuous updating of medical knowledge graphs, integrates reasoning, and retrieves current external evidence, such as PubMed and WikiSearch. By dynamically linking new findings and complex medical concepts, AMG-RAG not only improves accuracy but also enhances interpretability in medical queries. Evaluations on the MEDQA and MEDMCQA benchmarks demonstrate the effectiveness of AMG-RAG, achieving an F1 score of 74.1 percent on MEDQA and an accuracy of 66.34 percent on MEDMCQA, outperforming both comparable models and those 10 to 100 times larger. Notably, these improvements are achieved without increasing computational overhead, highlighting the critical role of automated knowledge graph generation and external evidence retrieval in delivering up-to-date, trustworthy medical insights. |
| 30 | Bridge: A Unified Framework to Knowledge Graph Completion via Language Models and Knowledge Representation | 2024-11-11 | 展开Knowledge graph completion (KGC) is a task of inferring missing triples based on existing Knowledge Graphs (KGs). Both structural and semantic information are vital for successful KGC. However, existing methods only use either the structural knowledge from the KG embeddings or the semantic information from pre-trained language models (PLMs), leading to suboptimal model performance. Moreover, since PLMs are not trained on KGs, directly using PLMs to encode triples may be inappropriate. To overcome these limitations, we propose a novel framework called Bridge, which jointly encodes structural and semantic information of KGs. Specifically, we strategically encode entities and relations separately by PLMs to better utilize the semantic knowledge of PLMs and enable structured representation learning via a structural learning principle. Furthermore, to bridge the gap between KGs and PLMs, we employ a self-supervised representation learning method called BYOL to fine-tune PLMs with two different views of a triple. Unlike BYOL, which uses augmentation methods to create two semantically similar views of the same image, potentially altering the semantic information. We strategically separate the triple into two parts to create different views, thus avoiding semantic alteration. Experiments demonstrate that Bridge outperforms the SOTA models on three benchmark datasets. |
| 31 | Core Knowledge Deficits in Multi-Modal Language Models | 2024-10-06 | 展开While Multi-modal Large Language Models (MLLMs) demonstrate impressive abilities over high-level perception and reasoning, their robustness in the wild remains limited, often falling short on tasks that are intuitive and effortless for humans. We examine the hypothesis that these deficiencies stem from the absence of core knowledge--rudimentary cognitive abilities innate to humans from early childhood. To explore the core knowledge representation in MLLMs, we introduce CoreCognition, a large-scale benchmark encompassing 12 core knowledge concepts grounded in developmental cognitive science. We evaluate 230 models with 11 different prompts, leading to a total of 2,530 data points for analysis. Our experiments uncover four key findings, collectively demonstrating core knowledge deficits in MLLMs: they consistently underperform and show reduced, or even absent, scalability on low-level abilities relative to high-level ones. Finally, we propose Concept Hacking, a novel controlled evaluation method that reveals MLLMs fail to progress toward genuine core knowledge understanding, but instead rely on shortcut learning as they scale. |
| 32 | MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension | 2024-09-20 | 展开Referring Expression Comprehension (REC), which aims to ground a local visual region via natural language, is a task that heavily relies on multimodal alignment. Most existing methods utilize powerful pre-trained models to transfer visual/linguistic knowledge by full fine-tuning. However, full fine-tuning the entire backbone not only breaks the rich prior knowledge embedded in the pre-training, but also incurs significant computational costs. Motivated by the recent emergence of Parameter-Efficient Transfer Learning (PETL) methods, we aim to solve the REC task in an effective and efficient manner. Directly applying these PETL methods to the REC task is inappropriate, as they lack the specific-domain abilities for precise local visual perception and visual-language alignment. Therefore, we propose a novel framework of Multimodal Prior-guided Parameter Efficient Tuning, namely MaPPER. Specifically, MaPPER comprises Dynamic Prior Adapters guided by an aligned prior, and Local Convolution Adapters to extract precise local semantics for better visual perception. Moreover, the Prior-Guided Text module is proposed to further utilize the prior for facilitating the cross-modal alignment. Experimental results on three widely-used benchmarks demonstrate that MaPPER achieves the best accuracy compared to the full fine-tuning and other PETL methods with only 1.41% tunable backbone parameters. Our code is available at https://github.com/liuting20/MaPPER. |
| 33 | AWF: Adaptive Weight Fusion for Enhanced Class Incremental Semantic Segmentation | 2024-09-13 | 展开Class Incremental Semantic Segmentation (CISS) aims to mitigate catastrophic forgetting by maintaining a balance between previously learned and newly introduced knowledge. Existing methods, primarily based on regularization techniques like knowledge distillation, help preserve old knowledge but often face challenges in effectively integrating new knowledge, resulting in limited overall improvement. Endpoints Weight Fusion (EWF) method, while simple, effectively addresses some of these limitations by dynamically fusing the model weights from previous steps with those from the current step, using a fusion parameter alpha determined by the relative number of previously known classes and newly introduced classes. However, the simplicity of the alpha calculation may limit its ability to fully capture the complexities of different task scenarios, potentially leading to suboptimal fusion outcomes. In this paper, we propose an enhanced approach called Adaptive Weight Fusion (AWF), which introduces an alternating training strategy for the fusion parameter, allowing for more flexible and adaptive weight integration. AWF achieves superior performance by better balancing the retention of old knowledge with the learning of new classes, significantly improving results on benchmark CISS tasks compared to the original EWF. And our experiment code will be released on Github. |
| 34 | HyperMono: A Monotonicity-aware Approach to Hyper-Relational Knowledge Representation | 2024-04-15 | 展开In a hyper-relational knowledge graph (HKG), each fact is composed of a main triple associated with attribute-value qualifiers, which express additional factual knowledge. The hyper-relational knowledge graph completion (HKGC) task aims at inferring plausible missing links in a HKG. Most existing approaches to HKGC focus on enhancing the communication between qualifier pairs and main triples, while overlooking two important properties that emerge from the monotonicity of the hyper-relational graphs representation regime. Stage Reasoning allows for a two-step reasoning process, facilitating the integration of coarse-grained inference results derived solely from main triples and fine-grained inference results obtained from hyper-relational facts with qualifiers. In the initial stage, coarse-grained results provide an upper bound for correct predictions, which are subsequently refined in the fine-grained step. More generally, Qualifier Monotonicity implies that by attaching more qualifier pairs to a main triple, we may only narrow down the answer set, but never enlarge it. This paper proposes the HyperMono model for hyper-relational knowledge graph completion, which realizes stage reasoning and qualifier monotonicity. To implement qualifier monotonicity HyperMono resorts to cone embeddings. Experiments on three real-world datasets with three different scenario conditions demonstrate the strong performance of HyperMono when compared to the SoTA. |
| 35 | ChatDBG: Augmenting Debugging with Large Language Models | 2024-03-25 | 展开Debugging is a critical but challenging task for programmers. This paper proposes ChatDBG, an AI-powered debugging assistant. ChatDBG integrates large language models (LLMs) to significantly enhance the capabilities and user-friendliness of conventional debuggers. ChatDBG lets programmers engage in a collaborative dialogue with the debugger, allowing them to pose complex questions about program state, perform root cause analysis for crashes or assertion failures, and explore open-ended queries like "why is x null?". To handle these queries, ChatDBG grants the LLM autonomy to "take the wheel": it can act as an independent agent capable of querying and controlling the debugger to navigate through stacks and inspect program state. It then reports its findings and yields back control to the programmer. By leveraging the real-world knowledge embedded in LLMs, ChatDBG can diagnose issues identifiable only through the use of domain-specific reasoning. Our ChatDBG prototype integrates with standard debuggers including LLDB and GDB for native code and Pdb for Python. Our evaluation across a diverse set of code, including C/C++ code with known bugs and a suite of Python code including standalone scripts and Jupyter notebooks, demonstrates that ChatDBG can successfully analyze root causes, explain bugs, and generate accurate fixes for a wide range of real-world errors. For the Python programs, a single query led to an actionable bug fix 67% of the time; one additional follow-up query increased the success rate to 85%. ChatDBG has seen rapid uptake; it has already been downloaded more than 75,000 times. |
| 36 | FedDTG:Federated Data-Free Knowledge Distillation via Three-Player Generative Adversarial Networks | 2022-01-10 | 展开While existing federated learning approaches primarily focus on aggregating local models to construct a global model, in realistic settings, some clients may be reluctant to share their private models due to the inclusion of privacy-sensitive information. Knowledge distillation, which can extract model knowledge without accessing model parameters, is well-suited for this federated scenario. However, most distillation methods in federated learning (federated distillation) require a proxy dataset, which is difficult to obtain in the real world. Therefore, in this paper, we introduce a distributed three-player Generative Adversarial Network (GAN) to implement data-free mutual distillation and propose an effective method called FedDTG. We confirmed that the fake samples generated by GAN can make federated distillation more efficient and robust. Additionally, the distillation process between clients can deliver good individual client performance while simultaneously acquiring global knowledge and protecting data privacy. Our extensive experiments on benchmark vision datasets demonstrate that our method outperforms other federated distillation algorithms in terms of generalization. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Deep Reinforcement Learning Xiangqi Player with Monte Carlo Tree Search | 2025-06-18 | 展开This paper presents a Deep Reinforcement Learning (DRL) system for Xiangqi (Chinese Chess) that integrates neural networks with Monte Carlo Tree Search (MCTS) to enable strategic self-play and self-improvement. Addressing the underexplored complexity of Xiangqi, including its unique board layout, piece movement constraints, and victory conditions, our approach combines policy-value networks with MCTS to simulate move consequences and refine decision-making. By overcoming challenges such as Xiangqi's high branching factor and asymmetrical piece dynamics, our work advances AI capabilities in culturally significant strategy games while providing insights for adapting DRL-MCTS frameworks to domain-specific rule systems. |
| 2 | Circular Game Coloring of Signed Graphs | 2025-05-27 | 展开We extend the theory of circular game chromatic numbers to signed graphs by defining the invariant |
| 3 | Computational and Algebraic Structure of Board Games | 2025-02-18 | 展开We provide two methodologies in the area of computation theory to solve optimal strategies for board games such as Xi Gua Qi and Go. From experimental results, we find relevance to graph theory, matrix representation, and mathematical consciousness. We prove that the decision strategy of movement for Xi Gua Qi and Chinese checker games belongs to a subset that is neither a ring nor a group over set Y={-1,0,1}. Additionally, the movement for any board game with two players belongs to a subset that is neither a ring nor a group from the razor of Occam. We derive the closed form of the transition matrix for any board game with two players such as chess and Chinese chess. We discover that the element of the transition matrix belongs to a rational number. We propose a different methodology based on algebra theory to analyze the complexity of board games in their entirety, instead of being limited solely to endgame results. It is probable that similar decision processes of people may also belong to a matrix representation that is neither a ring nor a group. |
| 4 | RemoteChess: Enhancing Older Adults' Social Connectedness via Designing a Virtual Reality Chinese Chess (Xiangqi) Community | 2025-02-17 | 展开The decline of social connectedness caused by distance and physical limitations severely affects older adults' well-being and mental health. While virtual reality (VR) is promising for older adults to socialize remotely, existing social VR designs primarily focus on verbal communication (e.g., reminiscent, chat). Actively engaging in shared activities is also an important aspect of social connection. We designed RemoteChess, which constructs a social community and a culturally relevant activity (i.e., Chinese chess) for older adults to play while engaging in social interaction. We conducted a user study with groups of older adults interacting with each other through RemoteChess. Our findings indicate that RemoteChess enhanced participants' social connectedness by offering familiar environments, culturally relevant social catalysts, and asymmetric interactions. We further discussed design guidelines for designing culturally relevant social activities in VR to promote social connectedness for older adults. |
| 5 | Temperatures of Robin Hood | 2025-01-13 | 展开Cumulative Games were introduced by Larsson, Meir, and Zick (2020) to bridge some conceptual and technical gaps between Combinatorial Game Theory (CGT) and Economic Game Theory. The partizan ruleset {\sc Robin Hood} is an instance of a Cumulative Game, viz., {\sc Wealth Nim}. It is played on multiple heaps, each associated with a pair of cumulations, interpreted here as wealth. Each player chooses one of the heaps, removes tokens from that heap not exceeding their own wealth, while simultaneously diminishing the other player's wealth by the same amount. In CGT, the {\em temperature} of a {\em disjunctive sum} game component is an estimate of the urgency of moving first in that component. It turns out that most of the positions of {\sc Robin Hood} are {\em hot}. The temperature of {\sc Robin Hood} on a single large heap shows a dichotomy in behavior depending on the ratio of the wealths of the players. Interestingly, this bifurcation is related to Pingala (Fibonacci) sequences and the Golden Ratio |
| 6 | On Conway's Numbers and Games, the Von Neumann Universe, and Pure Set Theory | 2025-01-08 | 展开We take up Dedekind's question ''Was sind und was sollen die Zahlen?'' (''What are numbers, and would should they be?''), with the aim to describe the place that Conway's (Surreal) Numbers and Games take, or deserve to take, in the whole of mathematics. Rather than just reviewing the work of Conway, and subsequent one by Gonshor, Alling, Ehrlich, and others, we propose a new setting which puts the theory of surreal numbers onto the firm ground of ''pure'' set theory. This approach is closely related to Gonshor's one by ''sign expansions'', but appears to be significantly simpler and clearer, and hopefully may contribute to realizing that ''surreal'' numbers are by no means surrealistic, goofy or wacky. They could, and probably should, play a central role in mathematics. We discuss the interplay between the various approaches to surreal numbers, and analyze the link with Conway's original approach via Combinatorial Game Theory (CGT). To clarify this, we propose to call pure set theory the algebraic theory of pure sets, or in other terms, of the algebraic structures of the von Neumann universe. This topic may be interesting in its own right: it puts CGT into a broad context which has a strong ''quantum flavor'', and where Conway's numbers (as well as their analogue, the nimbers) arise naturally. |
| 7 | Complete Implementation of WXF Chinese Chess Rules | 2024-12-23 | 展开Unlike repetitions in Western Chess where all repetitions are draws, repetitions in Chinese Chess could result in a win, draw, or loss depending on the kind of repetition being made by both players. One of the biggest hurdles facing Chinese Chess application development is a proper system for judging games correctly. This paper introduces a complete algorithm for ruling the WXF rules correctly in all 110 example cases found in the WXF manual. We introduce several novel optimizations for speeding up the repetition handling without compromising the program correctness. This algorithm is usable in engines, and we saw a total increase in playing strength by +10 point rating increase, or an increased 5% winrate when integrating this approach into our prototype engine. |
| 8 | Maker-Breaker on Galton-Watson trees | 2024-12-11 | 展开We consider the following combinatorial two-player game: On the random tree arising from a branching process, each round one player (Breaker) deletes an edge and by that removes the descendant and all its progeny, while the other (Maker) fixates an edge to permanently secure it from deletion. Breaker has won once the tree's root is contained in a finite component, otherwise Maker wins by building an infinite path starting at the root. It will be analyzed both as a positional game (the tree is known to both players at the start) and with more restrictive levels of information (the players essentially explore the tree during the game). Reading the number of available edges for play as a random walk on |
| 9 | Relationship between misère NIM and two-player GOISHI HIROI | 2024-12-05 | 展开In combinatorial game theory, there are two famous winning conventions, normal play and mis`ere play. Under normal play convention, the winner is the player who moves last and under mis`ere play convention, the loser is the player who moves last. The difference makes these conventions completely different, and usually, games under mis`ere play convention is much difficult to analyze than games under normal play convention. In this study, we show an interesting relationship between rulesets under different winning conventions; we can determine the winner of two-player GOISHI HIROI under normal play convention by using NIM under mis`ere play convention. We also analyze two-player GOISHI HIROI under mis`ere play convention. |
| 10 | The Game Value of Sequential Compounds of Integers and Stars | 2024-11-13 | 展开A combinatorial game is a two-player game without hidden information or chance elements. One of the major approaches to analyzing games in combinatorial game theory is to break down a given game position into a disjunctive sum of multiple sub-positions, then evaluate the game value of each component of the sum, and finally integrate these game values to find which player has a winning strategy in the whole position. Accordingly, finding the game value of a given position is a major topic in combinatorial game theory. The sequential compound proposed by Stromquist and Ullman is a combinatorial game consisting of two combinatorial games. In the sequential compound of games |
| 11 | A New 0(klog n) Algorithm for Josephus Problem | 2024-11-10 | 展开We present a new O(k log n) algorithm of the Josephus problem. The time complexity of our algorithm is O(k log n), and this time complexity is on a par with the existing O(k log n) algorithm. We do not have any recursion overhead or stack overflow because we do not use any recursion. Therefore, the space complexity of our algorithm is O(1), and ours is better than the existing O(k log n) algorithm in this respect. When k is small and n is large, our algorithm is better than the existing O(k log n) algorithm. This new algorithm is based on a relation between the Josephus problem and a maximum Nim of combinatorial game theory. |
| 12 | Mastering Chinese Chess AI (Xiangqi) Without Search | 2024-10-07 | 展开We have developed a high-performance Chinese Chess AI that operates without reliance on search algorithms. This AI has demonstrated the capability to compete at a level commensurate with the top 0.1% of human players. By eliminating the search process typically associated with such systems, this AI achieves a Queries Per Second (QPS) rate that exceeds those of systems based on the Monte Carlo Tree Search (MCTS) algorithm by over a thousandfold and surpasses those based on the AlphaBeta pruning algorithm by more than a hundredfold. The AI training system consists of two parts: supervised learning and reinforcement learning. Supervised learning provides an initial human-like Chinese chess AI, while reinforcement learning, based on supervised learning, elevates the strength of the entire AI to a new level. Based on this training system, we carried out enough ablation experiments and discovered that 1. The same parameter amount of Transformer architecture has a higher performance than CNN on Chinese chess; 2. Possible moves of both sides as features can greatly improve the training process; 3. Selective opponent pool, compared to pure self-play training, results in a faster improvement curve and a higher strength limit. 4. Value Estimation with Cutoff(VECT) improves the original PPO algorithm training process and we will give the explanation. |
| 13 | An Efficient Multi-Robot Arm Coordination Strategy for Pick-and-Place Tasks using Reinforcement Learning | 2024-09-20 | 展开We introduce a novel strategy for multi-robot sorting of waste objects using Reinforcement Learning. Our focus lies on finding optimal picking strategies that facilitate an effective coordination of a multi-robot system, subject to maximizing the waste removal potential. We realize this by formulating the sorting problem as an OpenAI gym environment and training a neural network with a deep reinforcement learning algorithm. The objective function is set up to optimize the picking rate of the robotic system. In simulation, we draw a performance comparison to an intuitive combinatorial game theory-based approach. We show that the trained policies outperform the latter and achieve up to 16% higher picking rates. Finally, the respective algorithms are validated on a hardware setup consisting of a two-robot sorting station able to process incoming waste objects through pick-and-place operations. |
| 14 | XQSV: A Structurally Variable Network to Imitate Human Play in Xiangqi | 2024-07-05 | 展开In this paper, we introduce an innovative deep learning architecture, termed Xiangqi Structurally Variable (XQSV), designed to emulate the behavioral patterns of human players in Xiangqi, or Chinese Chess. The unique attribute of XQSV is its capacity to alter its structural configuration dynamically, optimizing performance for the task based on the particular subset of data on which it is trained. We have incorporated several design improvements to significantly enhance the network's predictive accuracy, including a local illegal move filter, an Elo range partitioning, a sequential one-dimensional input, and a simulation of imperfect memory capacity. Empirical evaluations reveal that XQSV attains a predictive accuracy of approximately 40%, with its performance peaking within the trained Elo range. This indicates the model's success in mimicking the play behavior of individuals within that specific range. A three-terminal Turing Test was employed to demonstrate that the XQSV model imitates human behavior more accurately than conventional Xiangqi engines, rendering it indistinguishable from actual human opponents. Given the inherent nondeterminism in human gameplay, we propose two supplementary relaxed evaluation metrics. To our knowledge, XQSV represents the first model to mimic Xiangqi players. |
| 15 | Shogi and Frieze group | 2023-11-15 | 展开Shogi is a traditional Japanese strategy board game in the same family as chess, chaturanga, and xiangqi, and has been theoretically studied from various aspects. The research on recommended sequences of moves in each opening of shogi is called joseki; how to use a rook (Static Rook and Ranging Rook), or how to develop a castle, etc. Also, many pieces of tsume shogi, artistic shogi miniature problems, in which the opponent's king is checkmated by a series of checks, have been created involving various beautiful techniques such as "saw" and "puzzle ring". In addition, the rapid development of AI in recent years has led to the pursuit of the best possible moves in shogi. In this paper, we move away from the study of winning and losing in shogi and focus on the mathematical aspects of the movement of shogi pieces. We propose to correspond movements of shogi pieces to a set of geometrical patterns constructed by the shape of shogi pieces and representing the Frieze group through the condition regarding the neighborhood of arrangements of given shogi pieces. Although the discovery of this correspondence does not lead to a winning strategy for shogi, however, it does demonstrate a curious involvement between the traditional Japanese board game and Western mathematics. |
| 16 | JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Games | 2023-08-09 | 展开This paper presents an empirical exploration of non-transitivity in perfect-information games, specifically focusing on Xiangqi, a traditional Chinese board game comparable in game-tree complexity to chess and shogi. By analyzing over 10,000 records of human Xiangqi play, we highlight the existence of both transitive and non-transitive elements within the game's strategic structure. To address non-transitivity, we introduce the JiangJun algorithm, an innovative combination of Monte-Carlo Tree Search (MCTS) and Policy Space Response Oracles (PSRO) designed to approximate a Nash equilibrium. We evaluate the algorithm empirically using a WeChat mini program and achieve a Master level with a 99.41% win rate against human players. The algorithm's effectiveness in overcoming non-transitivity is confirmed by a plethora of metrics, such as relative population performance and visualization results. Our project site is available at \url{https://sites.google.com/view/jiangjun-site/}. |
| 17 | Niel's Chess -- Rules for Xiangqi | 2023-06-27 | 展开In this paper, the rules of Niel's Chess are adapted to the game of Xiangqi, following the idea that the River and the Palaces play an important role in restricting and enabling chess pieces in their movements. |
| 18 | On the complexity of Dark Chinese Chess | 2021-12-06 | 展开This paper provides a complexity analysis for the game of dark Chinese chess (a.k.a. "JieQi"), a variation of Chinese chess. Dark Chinese chess combines some of the most complicated aspects of board and card games, such as long-term strategy or planning, large state space, stochastic, and imperfect-information, which make it closer to the real world decision-making problem and pose great challenges to game AI. Here we design a self-play program to calculate the game tree complexity and average information set size of the game, and propose an algorithm to calculate the number of information sets. |
| 19 | A Note on Hardness Frameworks and Computational Complexity of Xiangqi and Janggi | 2019-03-30 | 展开We review NP-hardness framework and PSPACE-hardness framework for a type of 2D platform games. We introduce a EXPTIME-hardness framework by defining some new gadgets. We use these hardness frameworks to analyse computational complexity of Xiangqi (Chinese Chess) and Janggi (Korean Chess). We construct all gadgets of the hardness frameworks in Xiangqi and Janggi. In conclusion, we prove that Xiangqi and Janggi are both EXPTIME-complete. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs | 2025-06-23 | 展开The effectiveness of AI debugging follows a predictable exponential decay pattern; most models lose 60-80% of their debugging capability within just 2-3 attempts, despite iterative debugging being a critical capability for practical code generation systems. We introduce the Debugging Decay Index (DDI), a mathematical framework that quantifies when debugging becomes ineffective and predicts intervention points. Our strategic fresh start approach shifts from exploitation to exploration at strategic points in the debugging process, demonstrating that well-timed interventions can rescue the effectiveness of debugging. DDI reveals a fundamental limitation in current AI debugging and provides the first quantitative framework for optimising iterative code generation strategies. |
| 2 | CodeMorph: Mitigating Data Leakage in Large Language Model Assessment | 2025-06-21 | 展开Concerns about benchmark leakage in large language models for code (Code LLMs) have raised issues of data contamination and inflated evaluation metrics. The diversity and inaccessibility of many training datasets make it difficult to prevent data leakage entirely, even with time lag strategies. Consequently, generating new datasets through code perturbation has become essential. However, existing methods often fail to produce complex and diverse variations, struggle with complex cross-file dependencies, and lack support for multiple programming languages, which limits their effectiveness in enhancing LLM evaluations for coding tasks. To fill this gap, we propose CodeMorph, an approach designed to support multiple programming languages while preserving cross-file dependencies to mitigate data leakage. CodeMorph consists of two main components that work together to enhance the perturbation process. The first component employs 26 semantic-preserving transformation methods to iteratively perturb code, generating diverse variations while ensuring that the modified code remains compilable. The second component introduces a genetic algorithm-based selection algorithm, PESO, to identify the more effective perturbation method for each iteration by targeting lower similarity scores between the perturbed and original code, thereby enhancing overall perturbation effectiveness. Experimental results demonstrate that after applying CodeMorph, the accuracy of the LLM on code completion tasks across five programming languages decreased by an average of 24.67%, with Python showing the most significant reduction at 45%. The similarity score of code optimized by PESO is, on average, 7.01% lower than that of randomly perturbed code, peaking at a reduction of 42.86%. |
| 3 | Re-Evaluating Code LLM Benchmarks Under Semantic Mutation | 2025-06-20 | 展开In the era of large language models (LLMs), code benchmarks have become an important research area in software engineering and are widely used by practitioners. These benchmarks evaluate the performance of LLMs on specific code-related tasks, such as code understanding and generation. A critical step in constructing code benchmarks is the design of prompts. However, as existing code benchmarks typically rely on a single prompt template per task, they are prone to the issue of prompt sensitivity, where minor prompt variations could result in substantial performance variations, leading to unreliable evaluations of model capabilities. While previous studies have explored prompt sensitivity, their experimental designs and findings are limited to traditional natural language processing (NLP) tasks. In this paper, we present an empirical study to investigate prompt sensitivity in code benchmarks. We first propose a general framework that modifies prompt templates in a manner that preserves both their semantics and their structure as much as possible. Based on the framework, we conduct extensive experiments across eight code benchmark tasks on 10 representative open-source LLMs, with each task featuring 100 semantically similar prompt templates. We then analyze the evaluation results using various statistical metrics, focusing on both absolute and relative model performance. Our findings suggest that even slight prompt variations can lead to significant shifts in performance. Additionally, we observe that such variations can introduce inconsistencies in the performance rankings across different models. These insights highlight the need for considering prompt sensitivity when designing future code benchmarks, to ensure more reliable and accurate evaluation of LLM capabilities. |
| 4 | From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation? | 2025-05-24 | 展开Post-processing is crucial for the automatic evaluation of LLMs in fill-in-the-middle (FIM) code generation due to the frequent presence of extraneous code in raw outputs. This extraneous generation suggests a lack of awareness regarding output boundaries, requiring truncation for effective evaluation. The determination of an optimal truncation strategy, however, often proves intricate, particularly when the scope includes several programming languages. This study investigates the necessity of post-processing instruction-tuned LLM outputs. Our findings reveal that supervised fine-tuning significantly enhances FIM code generation, enabling LLMs to generate code that seamlessly integrates with the surrounding context. Evaluating our fine-tuned \texttt{Qwen2.5-Coder} (base and instruct) models on HumanEval Infilling and SAFIM benchmarks demonstrates improved performances without post-processing, especially when the \emph{middle} consist of complete lines. However, post-processing of the LLM outputs remains necessary when the \emph{middle} is a random span of code. |
| 5 | LongCodeBench: Evaluating Coding LLMs at 1M Context Windows | 2025-05-12 | 展开Context lengths for models have grown rapidly, from thousands to millions of tokens in just a few years. The extreme context sizes of modern long-context models have made it difficult to construct realistic long-context benchmarks -- not only due to the cost of collecting million-context tasks but also in identifying realistic scenarios that require significant contexts. We identify code comprehension and repair as a natural testbed and challenge task for long-context models and introduce LongCodeBench (LCB), a benchmark to test LLM coding abilities in long-context scenarios. Our benchmark tests both the comprehension and repair capabilities of LCLMs in realistic and important settings by drawing from real-world GitHub issues and constructing QA (LongCodeQA) and bug fixing (LongSWE-Bench) tasks. We carefully stratify the complexity of our benchmark, enabling us to evaluate models across different scales -- ranging from Qwen2.5 14B Instruct to Google's flagship Gemini model. We find that long-context remains a weakness for all models, with performance drops such as from 29% to 3% for Claude 3.5 Sonnet, or from 70.2% to 40% for Qwen2.5. |
| 6 | Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey | 2024-12-29 | 展开Reinforcement learning (RL) has emerged as a powerful paradigm for enhancing large language models (LLMs) in code generation and optimization. This survey systematically reviews RL-driven techniques across the code development lifecycle, from compiler-level optimizations and resource allocation strategies to end-to-end code synthesis frameworks. We first examine classical and modern RL algorithms -- spanning policy gradients, actor-critic methods, human-feedback alignment, and preference-based optimization -- and their adaptations to the unique challenges of code generation, such as sparse and delayed rewards. Next, we analyze key benchmarks, datasets, and evaluation metrics that drive progress in RL-augmented Code LLMs. Finally, we identify open problems, including the need for richer feedback sources, support for low-level and domain-specific languages, and methods to reduce computational overhead. By consolidating current insights and outlining future directions, this work aims to guide researchers and practitioners in leveraging RL to produce more robust, efficient, and human-aligned code generation systems. |
| 7 | Context-Augmented Code Generation Using Programming Knowledge Graphs | 2024-10-09 | 展开Large Language Models (LLMs) and Code-LLMs (CLLMs) have significantly improved code generation, but, they frequently face difficulties when dealing with challenging and complex problems. Retrieval-Augmented Generation (RAG) addresses this issue by retrieving and integrating external knowledge at the inference time. However, retrieval models often fail to find most relevant context, and generation models, with limited context capacity, can hallucinate when given irrelevant data. We present a novel framework that leverages a Programming Knowledge Graph (PKG) to semantically represent and retrieve code. This approach enables fine-grained code retrieval by focusing on the most relevant segments while reducing irrelevant context through a tree-pruning technique. PKG is coupled with a re-ranking mechanism to reduce even more hallucinations by selectively integrating non-RAG solutions. We propose two retrieval approaches-block-wise and function-wise-based on the PKG, optimizing context granularity. Evaluations on the HumanEval and MBPP benchmarks show our method improves pass@1 accuracy by up to 20%, and outperforms state-of-the-art models by up to 34% on MBPP. Our contributions include PKG-based retrieval, tree pruning to enhance retrieval precision, a re-ranking method for robust solution selection and a Fill-in-the-Middle (FIM) enhancer module for automatic code augmentation with relevant comments and docstrings. |
| 8 | Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models | 2024-06-29 | 展开Large language models (LLMs) have brought a paradigm shift to the field of code generation, offering the potential to enhance the software development process. However, previous research mainly focuses on the accuracy of code generation, while coding style differences between LLMs and human developers remain under-explored. In this paper, we empirically analyze the differences in coding style between the code generated by mainstream Code LLMs and the code written by human developers, and summarize coding style inconsistency taxonomy. Specifically, we first summarize the types of coding style inconsistencies by manually analyzing a large number of generation results. We then compare the code generated by Code LLMs with the code written by human programmers in terms of readability, conciseness, and robustness. The results reveal that LLMs and developers have different coding styles. Additionally, we study the possible causes of these inconsistencies and provide some solutions to alleviate the problem. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Research on Comprehensive Classroom Evaluation System Based on Multiple AI Models | 2025-06-29 | 展开The promotion of the national education digitalization strategy has facilitated the development of teaching quality evaluation towards all-round, process-oriented, precise, and intelligent directions, inspiring explorations into new methods and technologies for educational quality assurance. Classroom teaching evaluation methods dominated by teaching supervision and student teaching evaluation suffer from issues such as low efficiency, strong subjectivity, and limited evaluation dimensions. How to further advance intelligent and objective evaluation remains a topic to be explored. This paper, based on image recognition technology, speech recognition technology, and AI large language models, develops a comprehensive evaluation system that automatically generates evaluation reports and optimization suggestions from two dimensions: teacher teaching ability and classroom teaching effectiveness. This study establishes a closed-loop classroom evaluation model that comprehensively evaluates student and teaching conditions based on multi-dimensional data throughout the classroom teaching process, and further analyzes the data to guide teaching improvement. It meets the requirements of all-round and process-oriented classroom evaluation in the era of digital education, effectively solves the main problems of manual evaluation methods, and provides data collection and analysis methods as well as technologies for relevant research on educational teaching evaluation. |
| 2 | Mind the Gap: Entity-Preserved Context-Aware ASR Structured Transcriptions | 2025-06-28 | 展开Automatic Speech Recognition (ASR) systems, such as Whisper, achieve high transcription accuracy but struggle with named entities and numerical data, especially when proper formatting is required. These issues increase word error rate (WER) and impair semantic understanding in critical domains like legal, financial, and medical applications. We propose a novel training approach that extends the semantic context of ASR models by adding overlapping context windows during training. By sliding 5-second overlaps on both sides of 30-second chunks, we create a 40-second "effective semantic window," improving entity recognition and formatting while focusing predictions on the central 30 seconds. To address entities spanning chunk boundaries, we reassign such entities entirely to the right-hand chunk, ensuring proper formatting. Additionally, enriched training data with embedded entity labels enables the model to learn both recognition and type-specific formatting. Evaluated on the Spoken Wikipedia dataset, our method improves performance across semantic tasks, including named entity recognition (NER) and entity formatting. These results highlight the effectiveness of context-aware training in addressing ASR limitations for long-form transcription and complex entity recognition tasks. |
| 3 | Boosting CTC-Based ASR Using LLM-Based Intermediate Loss Regularization | 2025-06-28 | 展开End-to-end (E2E) automatic speech recognition (ASR) systems have revolutionized the field by integrating all components into a single neural network, with attention-based encoder-decoder models achieving state-of-the-art performance. However, their autoregressive decoding process limits inference speed, making them unsuitable for real-time applications. In contrast, CTC-based models offer faster, non-autoregressive decoding but struggle to model linguistic dependencies effectively. Addressing this challenge, we propose a novel auxiliary loss framework called Language-Aware Intermediate Loss (LAIL) to enhance CTC-based ASR using the linguistic knowledge of large language models (LLMs). By attaching connector layers to intermediate encoder layers, LAIL maps outputs to the embedding space of an LLM and computes a causal language modeling loss during training. This approach enhances linguistic modeling while preserving the computational efficiency of CTC decoding. Using the Conformer architecture and various LLaMA models, we demonstrate significant improvements in Word Error Rate (WER) on the LibriSpeech, TEDLIUM2, and WSJ corpora, achieving state-of-the-art performance for CTC-based ASR with minimal computational overhead. |
| 4 | A Self-Training Approach for Whisper to Enhance Long Dysarthric Speech Recognition | 2025-06-28 | 展开Dysarthric speech recognition (DSR) enhances the accessibility of smart devices for dysarthric speakers with limited mobility. Previously, DSR research was constrained by the fact that existing datasets typically consisted of isolated words, command phrases, and a limited number of sentences spoken by a few individuals. This constrained research to command-interaction systems and speaker adaptation. The Speech Accessibility Project (SAP) changed this by releasing a large and diverse English dysarthric dataset, leading to the SAP Challenge to build speaker- and text-independent DSR systems. We enhanced the Whisper model's performance on long dysarthric speech via a novel self-training method. This method increased training data and adapted the model to handle potentially incomplete speech segments encountered during inference. Our system achieved second place in both Word Error Rate and Semantic Score in the SAP Challenge. |
| 5 | Speaker Targeting via Self-Speaker Adaptation for Multi-talker ASR | 2025-06-27 | 展开We propose a self-speaker adaptation method for streaming multi-talker automatic speech recognition (ASR) that eliminates the need for explicit speaker queries. Unlike conventional approaches requiring target speaker embeddings or enrollment audio, our technique dynamically adapts individual ASR instances through speaker-wise speech activity prediction. The key innovation involves injecting speaker-specific kernels generated via speaker supervision activations into selected ASR encoder layers. This enables instantaneous speaker adaptation to target speakers while handling fully overlapped speech even in a streaming scenario. Experiments show state-of-the-art performance in both offline and streaming scenarios, demonstrating that our self-adaptive method effectively addresses severe speech overlap through streamlined speaker-focused recognition. The results validate the proposed self-speaker adaptation approach as a robust solution for multi-talker ASR under severe overlapping speech conditions. |
| 6 | Cross-lingual Data Selection Using Clip-level Acoustic Similarity for Enhancing Low-resource Automatic Speech Recognition | 2025-06-27 | 展开This paper presents a novel donor data selection method to enhance low-resource automatic speech recognition (ASR). While ASR performs well in high-resource languages, its accuracy declines in low-resource settings due to limited training data. A common solution is to leverage multilingual self-supervised learning (SSL) models with donor languages. However, existing methods rely on language-level similarity, overlooking clip-level variations. To address this limitation, we propose clip-wise acoustic token distribution similarity (CATDS), a fine-grained selection method that identifies acoustically relevant donor clips for better alignment with the target language. Unlike existing clip-level selection methods, our method aligns with the representation of SSL models and offers more challenging yet valuable samples. Experimental results show that CATDS outperforms traditional selection methods and can even utilize donor languages previously considered detrimental. |
| 7 | AI-Generated Song Detection via Lyrics Transcripts | 2025-06-23 | 展开The recent rise in capabilities of AI-based music generation tools has created an upheaval in the music industry, necessitating the creation of accurate methods to detect such AI-generated content. This can be done using audio-based detectors; however, it has been shown that they struggle to generalize to unseen generators or when the audio is perturbed. Furthermore, recent work used accurate and cleanly formatted lyrics sourced from a lyrics provider database to detect AI-generated music. However, in practice, such perfect lyrics are not available (only the audio is); this leaves a substantial gap in applicability in real-life use cases. In this work, we instead propose solving this gap by transcribing songs using general automatic speech recognition (ASR) models. We do this using several detectors. The results on diverse, multi-genre, and multi-lingual lyrics show generally strong detection performance across languages and genres, particularly for our best-performing model using Whisper large-v2 and LLM2Vec embeddings. In addition, we show that our method is more robust than state-of-the-art audio-based ones when the audio is perturbed in different ways and when evaluated on different music generators. Our code is available at https://github.com/deezer/robust-AI-lyrics-detection. |
| 8 | State-Space Models in Efficient Whispered and Multi-dialect Speech Recognition | 2025-06-20 | 展开Whispered speech recognition presents significant challenges for conventional automatic speech recognition systems, particularly when combined with dialect variation. However, utilizing an efficient method to solve this problem using a low-range dataset and processing load is beneficial. This paper proposes a solution using a Mamba-based state-space model and four fine-tuned self-supervised models consisting of Wav2Vec2, WavLM, HuBERT, and Whisper to address the dual challenges of whispered speech and dialect diversity. Based on our knowledge, this represents the best performance reported on the wTIMIT and CHAINS datasets for whispered speech recognition. We trained the models using whispered and normal speech data across Singaporean, US, and Irish dialects. The findings demonstrated that utilizing the proposed Mamba-based model could work as a highly efficient model trained with low amounts of whispered data to simultaneously work on whispered and normal speech recognition. The code for this work is freely available. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | Validation of AI-Based 3D Human Pose Estimation in a Cyber-Physical Environment | 2025-06-30 | 展开Ensuring safe and realistic interactions between automated driving systems and vulnerable road users (VRUs) in urban environments requires advanced testing methodologies. This paper presents a test environment that combines a Vehiclein-the-Loop (ViL) test bench with a motion laboratory, demonstrating the feasibility of cyber-physical (CP) testing of vehicle-pedestrian and vehicle-cyclist interactions. Building upon previous work focused on pedestrian localization, we further validate a human pose estimation (HPE) approach through a comparative analysis of real-world (RW) and virtual representations of VRUs. The study examines the perception of full-body motion using a commercial monocular camera-based 3Dskeletal detection AI. The virtual scene is generated in Unreal Engine 5, where VRUs are animated in real time and projected onto a screen to stimulate the camera. The proposed stimulation technique ensures the correct perspective, enabling realistic vehicle perception. To assess the accuracy and consistency of HPE across RW and CP domains, we analyze the reliability of detections as well as variations in movement trajectories and joint estimation stability. The validation includes dynamic test scenarios where human avatars, both walking and cycling, are monitored under controlled conditions. Our results show a strong alignment in HPE between RW and CP test conditions for stable motion patterns, while notable inaccuracies persist under dynamic movements and occlusions, particularly for complex cyclist postures. These findings contribute to refining CP testing approaches for evaluating next-generation AI-based vehicle perception and to enhancing interaction models of automated vehicles and VRUs in CP environments. |
| 2 | MGPRL: Distributed Multi-Gaussian Processes for Wi-Fi-based Multi-Robot Relative Localization in Large Indoor Environments | 2025-06-30 | 展开Relative localization is a crucial capability for multi-robot systems operating in GPS-denied environments. Existing approaches for multi-robot relative localization often depend on costly or short-range sensors like cameras and LiDARs. Consequently, these approaches face challenges such as high computational overhead (e.g., map merging) and difficulties in disjoint environments. To address this limitation, this paper introduces MGPRL, a novel distributed framework for multi-robot relative localization using convex-hull of multiple Wi-Fi access points (AP). To accomplish this, we employ co-regionalized multi-output Gaussian Processes for efficient Radio Signal Strength Indicator (RSSI) field prediction and perform uncertainty-aware multi-AP localization, which is further coupled with weighted convex hull-based alignment for robust relative pose estimation. Each robot predicts the RSSI field of the environment by an online scan of APs in its environment, which are utilized for position estimation of multiple APs. To perform relative localization, each robot aligns the convex hull of its predicted AP locations with that of the neighbor robots. This approach is well-suited for devices with limited computational resources and operates solely on widely available Wi-Fi RSSI measurements without necessitating any dedicated pre-calibration or offline fingerprinting. We rigorously evaluate the performance of the proposed MGPRL in ROS simulations and demonstrate it with real-world experiments, comparing it against multiple state-of-the-art approaches. The results showcase that MGPRL outperforms existing methods in terms of localization accuracy and computational efficiency. Finally, we open source MGPRL as a ROS package https://github.com/herolab-uga/MGPRL. |
| 3 | TVG-SLAM: Robust Gaussian Splatting SLAM with Tri-view Geometric Constraints | 2025-06-29 | 展开Recent advances in 3D Gaussian Splatting (3DGS) have enabled RGB-only SLAM systems to achieve high-fidelity scene representation. However, the heavy reliance of existing systems on photometric rendering loss for camera tracking undermines their robustness, especially in unbounded outdoor environments with severe viewpoint and illumination changes. To address these challenges, we propose TVG-SLAM, a robust RGB-only 3DGS SLAM system that leverages a novel tri-view geometry paradigm to ensure consistent tracking and high-quality mapping. We introduce a dense tri-view matching module that aggregates reliable pairwise correspondences into consistent tri-view matches, forming robust geometric constraints across frames. For tracking, we propose Hybrid Geometric Constraints, which leverage tri-view matches to construct complementary geometric cues alongside photometric loss, ensuring accurate and stable pose estimation even under drastic viewpoint shifts and lighting variations. For mapping, we propose a new probabilistic initialization strategy that encodes geometric uncertainty from tri-view correspondences into newly initialized Gaussians. Additionally, we design a Dynamic Attenuation of Rendering Trust mechanism to mitigate tracking drift caused by mapping latency. Experiments on multiple public outdoor datasets show that our TVG-SLAM outperforms prior RGB-only 3DGS-based SLAM systems. Notably, in the most challenging dataset, our method improves tracking robustness, reducing the average Absolute Trajectory Error (ATE) by 69.0% while achieving state-of-the-art rendering quality. The implementation of our method will be released as open-source. |
| 4 | Deterministic Object Pose Confidence Region Estimation | 2025-06-28 | 展开6D pose confidence region estimation has emerged as a critical direction, aiming to perform uncertainty quantification for assessing the reliability of estimated poses. However, current sampling-based approach suffers from critical limitations that severely impede their practical deployment: 1) the sampling speed significantly decreases as the number of samples increases. 2) the derived confidence regions are often excessively large. To address these challenges, we propose a deterministic and efficient method for estimating pose confidence regions. Our approach uses inductive conformal prediction to calibrate the deterministically regressed Gaussian keypoint distributions into 2D keypoint confidence regions. We then leverage the implicit function theorem to propagate these keypoint confidence regions directly into 6D pose confidence regions. This method avoids the inefficiency and inflated region sizes associated with sampling and ensembling. It provides compact confidence regions that cover the ground-truth poses with a user-defined confidence level. Experimental results on the LineMOD Occlusion and SPEED datasets show that our method achieves higher pose estimation accuracy with reduced computational time. For the same coverage rate, our method yields significantly smaller confidence region volumes, reducing them by up to 99.9% for rotations and 99.8% for translations. The code will be available soon. |
| 5 | Evaluating Pointing Gestures for Target Selection in Human-Robot Collaboration | 2025-06-27 | 展开Pointing gestures are a common interaction method used in Human-Robot Collaboration for various tasks, ranging from selecting targets to guiding industrial processes. This study introduces a method for localizing pointed targets within a planar workspace. The approach employs pose estimation, and a simple geometric model based on shoulder-wrist extension to extract gesturing data from an RGB-D stream. The study proposes a rigorous methodology and comprehensive analysis for evaluating pointing gestures and target selection in typical robotic tasks. In addition to evaluating tool accuracy, the tool is integrated into a proof-of-concept robotic system, which includes object detection, speech transcription, and speech synthesis to demonstrate the integration of multiple modalities in a collaborative application. Finally, a discussion over tool limitations and performance is provided to understand its role in multimodal robotic systems. All developments are available at: https://github.com/NMKsas/gesture_pointer.git. |
| 6 | What Makes a Dribble Successful? Insights From 3D Pose Tracking Data | 2025-06-25 | 展开Data analysis plays an increasingly important role in soccer, offering new ways to evaluate individual and team performance. One specific application is the evaluation of dribbles: one-on-one situations where an attacker attempts to bypass a defender with the ball. While previous research has primarily relied on 2D positional tracking data, this fails to capture aspects like balance, orientation, and ball control, limiting the depth of current insights. This study explores how pose tracking data (capturing players' posture and movement in three dimensions) can improve our understanding of dribbling skills. We extract novel pose-based features from 1,736 dribbles in the 2022/23 Champions League season and evaluate their impact on dribble success. Our results indicate that features capturing the attacker's balance and the alignment of the orientation between the attacker and defender are informative for predicting dribble success. Incorporating these pose-based features on top of features derived from traditional 2D positional data leads to a measurable improvement in model performance. |
| 7 | RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Tracking | 2025-06-20 | 展开We introduce a robust framework, RGBTrack, for real-time 6D pose estimation and tracking that operates solely on RGB data, thereby eliminating the need for depth input for such dynamic and precise object pose tracking tasks. Building on the FoundationPose architecture, we devise a novel binary search strategy combined with a render-and-compare mechanism to efficiently infer depth and generate robust pose hypotheses from true-scale CAD models. To maintain stable tracking in dynamic scenarios, including rapid movements and occlusions, RGBTrack integrates state-of-the-art 2D object tracking (XMem) with a Kalman filter and a state machine for proactive object pose recovery. In addition, RGBTrack's scale recovery module dynamically adapts CAD models of unknown scale using an initial depth estimate, enabling seamless integration with modern generative reconstruction techniques. Extensive evaluations on benchmark datasets demonstrate that RGBTrack's novel depth-free approach achieves competitive accuracy and real-time performance, making it a promising practical solution candidate for application areas including robotics, augmented reality, and computer vision. The source code for our implementation will be made publicly available at https://github.com/GreatenAnoymous/RGBTrack.git. |
| 8 | Full-Pose Tracking via Robust Control for Over-Actuated Multirotors | 2025-06-19 | 展开This paper presents a robust cascaded control architecture for over-actuated multirotors. It extends the Incremental Nonlinear Dynamic Inversion (INDI) control combined with structured H_inf control, initially proposed for under-actuated multirotors, to a broader range of multirotor configurations. To achieve precise and robust attitude and position tracking, we employ a weighted least-squares geometric guidance control allocation method, formulated as a quadratic optimization problem, enabling full-pose tracking. The proposed approach effectively addresses key challenges, such as preventing infeasible pose references and enhancing robustness against disturbances, as well as considering multirotor's actual physical limitations. Numerical simulations with an over-actuated hexacopter validate the method's effectiveness, demonstrating its adaptability to diverse mission scenarios and its potential for real-world aerial applications. |
| 9 | Fluoroscopic Shape and Pose Tracking of Catheters with Custom Radiopaque Markers | 2025-06-11 | 展开Safe navigation of steerable and robotic catheters in the cerebral vasculature requires awareness of the catheters shape and pose. Currently, a significant perception burden is placed on interventionalists to mentally reconstruct and predict catheter motions from biplane fluoroscopy images. Efforts to track these catheters are limited to planar segmentation or bulky sensing instrumentation, which are incompatible with microcatheters used in neurointervention. In this work, a catheter is equipped with custom radiopaque markers arranged to enable simultaneous shape and pose estimation under biplane fluoroscopy. A design measure is proposed to guide the arrangement of these markers to minimize sensitivity to marker tracking uncertainty. This approach was deployed for microcatheters smaller than 2mm OD navigating phantom vasculature with shape tracking errors less than 1mm and catheter roll errors below 40 degrees. This work can enable steerable catheters to autonomously navigate under biplane imaging. |
| 10 | Mouse Lockbox Dataset: Behavior Recognition for Mice Solving Lockboxes | 2025-05-21 | 展开Machine learning and computer vision methods have a major impact on the study of natural animal behavior, as they enable the (semi-)automatic analysis of vast amounts of video data. Mice are the standard mammalian model system in most research fields, but the datasets available today to refine such methods focus either on simple or social behaviors. In this work, we present a video dataset of individual mice solving complex mechanical puzzles, so-called lockboxes. The more than 110 hours of total playtime show their behavior recorded from three different perspectives. As a benchmark for frame-level action classification methods, we provide human-annotated labels for all videos of two different mice, that equal 13% of our dataset. Our keypoint (pose) tracking-based action classification framework illustrates the challenges of automated labeling of fine-grained behaviors, such as the manipulation of objects. We hope that our work will help accelerate the advancement of automated action and behavior classification in the computational neuroscience community. Our dataset is publicly available at https://doi.org/10.14279/depositonce-23850 |
| 11 | BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports | 2025-02-28 | 展开Badminton, known for having the fastest ball speeds among all sports, presents significant challenges to the field of computer vision, including player identification, court line detection, shuttlecock trajectory tracking, and player stroke-type classification. In this paper, we introduce a novel video segmentation strategy to extract frames of each player's racket swing in a badminton broadcast match. These segmented frames are then processed by two existing models: one for Human Pose Estimation to obtain player skeletal joints, and the other for shuttlecock trajectory detection to extract shuttlecock trajectories. Leveraging these joints, trajectories, and player positions as inputs, we propose Badminton Stroke-type Transformer (BST) to classify player stroke-types in singles. To the best of our knowledge, experimental results demonstrate that our method outperforms the previous state-of-the-art on the largest publicly available badminton video dataset, ShuttleSet, which shows that effectively leveraging ball trajectory is likely to be a trend for racket sports action recognition. |
| 12 | PoI: A Filter to Extract Pixel of Interest from Novel View Synthesis for Scene Coordinate Regression | 2025-02-07 | 展开Novel View Synthesis (NVS) techniques, notably Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), can augment camera pose estimation by extending and diversifying training data. However, images generated by these methods are often plagued by spatial artifacts such as blurring and ghosting, undermining their reliability as training data for camera pose estimation. This limitation is particularly critical for Scene Coordinate Regression (SCR) methods, which aim at pixel-level 3D coordinate estimation, because rendering artifacts directly lead to estimation inaccuracies. To address this challenge, we propose a dual-criteria filtering mechanism that dynamically identifies and discards suboptimal pixels during training. The dual-criteria filter evaluates two concurrent metrics: (1) real-time SCR reprojection error, and (2) gradient threshold, across the coordinate regression domain. In addition, for visual localization problems in sparse-input scenarios, it becomes even more necessary to use NVS-generated data to assist localization. We design a coarse-to-fine Points of Interest (PoI) variant using sparse-input NVS to solve this problem. Experiments across indoor and outdoor benchmarks confirm our method's efficacy, achieving state-of-the-art localization accuracy while maintaining computational efficiency. |
| 13 | G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation | 2024-11-27 | 展开Recent advances in imitation learning for 3D robotic manipulation have shown promising results with diffusion-based policies. However, achieving human-level dexterity requires seamless integration of geometric precision and semantic understanding. We present G3Flow, a novel framework that constructs real-time semantic flow, a dynamic, object-centric 3D semantic representation by leveraging foundation models. Our approach uniquely combines 3D generative models for digital twin creation, vision foundation models for semantic feature extraction, and robust pose tracking for continuous semantic flow updates. This integration enables complete semantic understanding even under occlusions while eliminating manual annotation requirements. By incorporating semantic flow into diffusion policies, we demonstrate significant improvements in both terminal-constrained manipulation and cross-object generalization. Extensive experiments across five simulation tasks show that G3Flow consistently outperforms existing approaches, achieving up to 68.3% and 50.1% average success rates on terminal-constrained manipulation and cross-object generalization tasks respectively. Our results demonstrate the effectiveness of G3Flow in enhancing real-time dynamic semantic feature understanding for robotic manipulation policies. |
| 14 | AsymDex: Asymmetry and Relative Coordinates for RL-based Bimanual Dexterity | 2024-11-20 | 展开We present Asymmetric Dexterity (AsymDex), a novel and simple reinforcement learning (RL) framework that can efficiently learn a large class of bimanual skills in multi-fingered hands without relying on demonstrations. Two crucial insights enable AsymDex to reduce the observation and action space dimensions and improve sample efficiency. First, true ambidexterity is rare in humans and most of us exhibit strong "handedness". Inspired by this observation, we assign complementary roles to each hand: the facilitating hand repositions and reorients one object, while the dominant hand performs complex manipulations to achieve the desired result (e.g., opening a bottle cap, or pouring liquids). Second, controlling the relative motion between the hands is crucial for coordination and synchronization of the two hands. As such, we design relative observation and action spaces and leverage a relative-pose tracking controller. Further, we propose a two-phase decomposition in which AsymDex can be readily integrated with recent advances in grasp learning to facilitate both the acquisition and manipulation of objects using two hands. Unlike existing RL-based methods for bimanual dexterity with multi-fingered hands, which are either sample inefficient or tailored to a specific task, AsymDex can efficiently learn a wide variety of bimanual skills that exhibit asymmetry. Detailed experiments on seven asymmetric bimanual dexterous manipulation tasks (four simulated and three real-world) reveal that AsymDex consistently outperforms strong baselines that challenge our design choices. The project website is at https://sites.google.com/view/asymdex-2025/. |
| 15 | Faster Model Predictive Control via Self-Supervised Initialization Learning | 2024-08-06 | 展开Optimization for robot control tasks, spanning various methodologies, includes Model Predictive Control (MPC). However, the complexity of the system, such as non-convex and non-differentiable cost functions and prolonged planning horizons often drastically increases the computation time, limiting MPC's real-world applicability. Prior works in speeding up the optimization have limitations on optimizing MPC running time directly and generalizing to hold out domains. To overcome this challenge, we develop a novel framework aiming at expediting optimization processes directly. In our framework, we combine offline self-supervised learning and online fine-tuning to improve the control performance and reduce optimization time. We demonstrate the success of our method on a novel and challenging Formula 1 track driving task. Comparing to single-phase training, our approach achieves a 19.4% reduction in optimization time and a 6.3% improvement in tracking accuracy on zero-shot tracks. |
| 16 | SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scale | 2024-06-11 | 展开A persistent challenge in sign language video processing, including the task of sign to written language translation, is how we learn representations of sign language in an effective and efficient way that preserves the important attributes of these languages, while remaining invariant to irrelevant visual differences. Informed by the nature and linguistics of signed languages, our proposed method focuses on just the most relevant parts in a signing video: the face, hands and body pose of the signer. However, instead of fully relying on pose estimation from off-the-shelf pose tracking models, which have inconsistent performance for hands and faces, we propose to learn a representation of the complex handshapes and facial expressions of sign languages in a self-supervised fashion. Our approach is based on learning from individual frames (rather than video sequences) and is therefore much more efficient than prior work on sign language pre-training. Compared to a recent model that established a new state of the art in sign language translation on the How2Sign dataset, our approach yields similar translation performance, using less than 3% of the compute. |
| 17 | Matching Anything by Segmenting Anything | 2024-06-06 | 展开The robust association of the same objects across video frames in complex scenes is crucial for many applications, especially Multiple Object Tracking (MOT). Current methods predominantly rely on labeled domain-specific video datasets, which limits the cross-domain generalization of learned similarity embeddings. We propose MASA, a novel method for robust instance association learning, capable of matching any objects within videos across diverse domains without tracking labels. Leveraging the rich object segmentation from the Segment Anything Model (SAM), MASA learns instance-level correspondence through exhaustive data transformations. We treat the SAM outputs as dense object region proposals and learn to match those regions from a vast image collection. We further design a universal MASA adapter which can work in tandem with foundational segmentation or detection models and enable them to track any detected objects. Those combinations present strong zero-shot tracking ability in complex domains. Extensive tests on multiple challenging MOT and MOTS benchmarks indicate that the proposed method, using only unlabeled static images, achieves even better performance than state-of-the-art methods trained with fully annotated in-domain video sequences, in zero-shot association. Project Page: https://matchinganything.github.io/ |
| 18 | Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser | 2024-03-07 | 展开Recently, diffusion-based methods for monocular 3D human pose estimation have achieved state-of-the-art (SOTA) performance by directly regressing the 3D joint coordinates from the 2D pose sequence. Although some methods decompose the task into bone length and bone direction prediction based on the human anatomical skeleton to explicitly incorporate more human body prior constraints, the performance of these methods is significantly lower than that of the SOTA diffusion-based methods. This can be attributed to the tree structure of the human skeleton. Direct application of the disentangled method could amplify the accumulation of hierarchical errors, propagating through each hierarchy. Meanwhile, the hierarchical information has not been fully explored by the previous methods. To address these problems, a Disentangled Diffusion-based 3D Human Pose Estimation method with Hierarchical Spatial and Temporal Denoiser is proposed, termed DDHPose. In our approach: (1) We disentangle the 3D pose and diffuse the bone length and bone direction during the forward process of the diffusion model to effectively model the human pose prior. A disentanglement loss is proposed to supervise diffusion model learning. (2) For the reverse process, we propose Hierarchical Spatial and Temporal Denoiser (HSTDenoiser) to improve the hierarchical modeling of each joint. Our HSTDenoiser comprises two components: the Hierarchical-Related Spatial Transformer (HRST) and the Hierarchical-Related Temporal Transformer (HRTT). HRST exploits joint spatial information and the influence of the parent joint on each joint for spatial modeling, while HRTT utilizes information from both the joint and its hierarchical adjacent joints to explore the hierarchical temporal correlations among joints. Code and models are available at https://github.com/Andyen512/DDHPose |
| 19 | Multi-Scale Memory Comparison for Zero-/Few-Shot Anomaly Detection | 2023-08-09 | 展开Anomaly detection has gained considerable attention due to its broad range of applications, particularly in industrial defect detection. To address the challenges of data collection, researchers have introduced zero-/few-shot anomaly detection techniques that require minimal normal images for each category. However, complex industrial scenarios often involve multiple objects, presenting a significant challenge. In light of this, we propose a straightforward yet powerful multi-scale memory comparison framework for zero-/few-shot anomaly detection. Our approach employs a global memory bank to capture features across the entire image, while an individual memory bank focuses on simplified scenes containing a single object. The efficacy of our method is validated by its remarkable achievement of 4th place in the zero-shot track and 2nd place in the few-shot track of the Visual Anomaly and Novelty Detection (VAND) competition. |
| 20 | Zero-Shot Anomaly Detection with Pre-trained Segmentation Models | 2023-06-15 | 展开This technical report outlines our submission to the zero-shot track of the Visual Anomaly and Novelty Detection (VAND) 2023 Challenge. Building on the performance of the WINCLIP framework, we aim to enhance the system's localization capabilities by integrating zero-shot segmentation models. In addition, we perform foreground instance segmentation which enables the model to focus on the relevant parts of the image, thus allowing the models to better identify small or subtle deviations. Our pipeline requires no external data or information, allowing for it to be directly applied to new datasets. Our team (Variance Vigilance Vanguard) ranked third in the zero-shot track of the VAND challenge, and achieve an average F1-max score of 81.5/24.2 at a sample/pixel level on the VisA dataset. |
| 21 | APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD | 2023-05-27 | 展开In this technical report, we briefly introduce our solution for the Zero/Few-shot Track of the Visual Anomaly and Novelty Detection (VAND) 2023 Challenge. For industrial visual inspection, building a single model that can be rapidly adapted to numerous categories without or with only a few normal reference images is a promising research direction. This is primarily because of the vast variety of the product types. For the zero-shot track, we propose a solution based on the CLIP model by adding extra linear layers. These layers are used to map the image features to the joint embedding space, so that they can compare with the text features to generate the anomaly maps. Besides, when the reference images are available, we utilize multiple memory banks to store their features and compare them with the features of the test images during the testing phase. In this challenge, our method achieved first place in the zero-shot track, especially excelling in segmentation with an impressive F1 score improvement of 0.0489 over the second-ranked participant. Furthermore, in the few-shot track, we secured the fourth position overall, with our classification F1 score of 0.8687 ranking first among all participating teams. |
| 22 | Unifying Tracking and Image-Video Object Detection | 2022-11-20 | 展开Objection detection (OD) has been one of the most fundamental tasks in computer vision. Recent developments in deep learning have pushed the performance of image OD to new heights by learning-based, data-driven approaches. On the other hand, video OD remains less explored, mostly due to much more expensive data annotation needs. At the same time, multi-object tracking (MOT) which requires reasoning about track identities and spatio-temporal trajectories, shares similar spirits with video OD. However, most MOT datasets are class-specific (e.g., person-annotated only), which constrains a model's flexibility to perform tracking on other objects. We propose TrIVD (Tracking and Image-Video Detection), the first framework that unifies image OD, video OD, and MOT within one end-to-end model. To handle the discrepancies and semantic overlaps of category labels across datasets, TrIVD formulates detection/tracking as grounding and reasons about object categories via visual-text alignments. The unified formulation enables cross-dataset, multi-task training, and thus equips TrIVD with the ability to leverage frame-level features, video-level spatio-temporal relations, as well as track identity associations. With such joint training, we can now extend the knowledge from OD data, that comes with much richer object category annotations, to MOT and achieve zero-shot tracking capability. Experiments demonstrate that multi-task co-trained TrIVD outperforms single-task baselines across all image/video OD and MOT tasks. We further set the first baseline on the new task of zero-shot tracking. |
| 23 | Exploring the Effectiveness of Self-supervised Learning and Classifier Chains in Emotion Recognition of Nonverbal Vocalizations | 2022-06-21 | 展开We present an emotion recognition system for nonverbal vocalizations (NVs) submitted to the ExVo Few-Shot track of the ICML Expressive Vocalizations Competition 2022. The proposed method uses self-supervised learning (SSL) models to extract features from NVs and uses a classifier chain to model the label dependency between emotions. Experimental results demonstrate that the proposed method can significantly improve the performance of this task compared to several baseline methods. Our proposed method obtained a mean concordance correlation coefficient (CCC) of |
| 24 | The Multi-speaker Multi-style Voice Cloning Challenge 2021 | 2021-04-05 | 展开The Multi-speaker Multi-style Voice Cloning Challenge (M2VoC) aims to provide a common sizable dataset as well as a fair testbed for the benchmarking of the popular voice cloning task. Specifically, we formulate the challenge to adapt an average TTS model to the stylistic target voice with limited data from target speaker, evaluated by speaker identity and style similarity. The challenge consists of two tracks, namely few-shot track and one-shot track, where the participants are required to clone multiple target voices with 100 and 5 samples respectively. There are also two sub-tracks in each track. For sub-track a, to fairly compare different strategies, the participants are allowed to use only the training data provided by the organizer strictly. For sub-track b, the participants are allowed to use any data publicly available. In this paper, we present a detailed explanation on the tasks and data used in the challenge, followed by a summary of submitted systems and evaluation results. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation | 2025-06-29 | 展开Single-image-to-3D models typically follow a sequential generation and reconstruction workflow. However, intermediate multi-view images synthesized by pre-trained generation models often lack cross-view consistency (CVC), significantly degrading 3D reconstruction performance. While recent methods attempt to refine CVC by feeding reconstruction results back into the multi-view generator, these approaches struggle with noisy and unstable reconstruction outputs that limit effective CVC improvement. We introduce AlignCVC, a novel framework that fundamentally re-frames single-image-to-3D generation through distribution alignment rather than relying on strict regression losses. Our key insight is to align both generated and reconstructed multi-view distributions toward the ground-truth multi-view distribution, establishing a principled foundation for improved CVC. Observing that generated images exhibit weak CVC while reconstructed images display strong CVC due to explicit rendering, we propose a soft-hard alignment strategy with distinct objectives for generation and reconstruction models. This approach not only enhances generation quality but also dramatically accelerates inference to as few as 4 steps. As a plug-and-play paradigm, our method, namely AlignCVC, seamlessly integrates various multi-view generation models with 3D reconstruction models. Extensive experiments demonstrate the effectiveness and efficiency of AlignCVC for single-image-to-3D generation. |
| 2 | DreamAnywhere: Object-Centric Panoramic 3D Scene Generation | 2025-06-25 | 展开Recent advances in text-to-3D scene generation have demonstrated significant potential to transform content creation across multiple industries. Although the research community has made impressive progress in addressing the challenges of this complex task, existing methods often generate environments that are only front-facing, lack visual fidelity, exhibit limited scene understanding, and are typically fine-tuned for either indoor or outdoor settings. In this work, we address these issues and propose DreamAnywhere, a modular system for the fast generation and prototyping of 3D scenes. Our system synthesizes a 360{\deg} panoramic image from text, decomposes it into background and objects, constructs a complete 3D representation through hybrid inpainting, and lifts object masks to detailed 3D objects that are placed in the virtual environment. DreamAnywhere supports immersive navigation and intuitive object-level editing, making it ideal for scene exploration, visual mock-ups, and rapid prototyping -- all with minimal manual modeling. These features make our system particularly suitable for low-budget movie production, enabling quick iteration on scene layout and visual tone without the overhead of traditional 3D workflows. Our modular pipeline is highly customizable as it allows components to be replaced independently. Compared to current state-of-the-art text and image-based 3D scene generation approaches, DreamAnywhere shows significant improvements in coherence in novel view synthesis and achieves competitive image quality, demonstrating its effectiveness across diverse and challenging scenarios. A comprehensive user study demonstrates a clear preference for our method over existing approaches, validating both its technical robustness and practical usefulness. |
| 3 | 3D Arena: An Open Platform for Generative 3D Evaluation | 2025-06-23 | 展开Evaluating Generative 3D models remains challenging due to misalignment between automated metrics and human perception of quality. Current benchmarks rely on image-based metrics that ignore 3D structure or geometric measures that fail to capture perceptual appeal and real-world utility. To address this gap, we present 3D Arena, an open platform for evaluating image-to-3D generation models through large-scale human preference collection using pairwise comparisons. Since launching in June 2024, the platform has collected 123,243 votes from 8,096 users across 19 state-of-the-art models, establishing the largest human preference evaluation for Generative 3D. We contribute the iso3d dataset of 100 evaluation prompts and demonstrate quality control achieving 99.75% user authenticity through statistical fraud detection. Our ELO-based ranking system provides reliable model assessment, with the platform becoming an established evaluation resource. Through analysis of this preference data, we present insights into human preference patterns. Our findings reveal preferences for visual presentation features, with Gaussian splat outputs achieving a 16.6 ELO advantage over meshes and textured models receiving a 144.1 ELO advantage over untextured models. We provide recommendations for improving evaluation methods, including multi-criteria assessment, task-oriented evaluation, and format-aware comparison. The platform's community engagement establishes 3D Arena as a benchmark for the field while advancing understanding of human-centered evaluation in Generative 3D. |
| 4 | DreamJourney: Perpetual View Generation with Video Diffusion Models | 2025-06-21 | 展开Perpetual view generation aims to synthesize a long-term video corresponding to an arbitrary camera trajectory solely from a single input image. Recent methods commonly utilize a pre-trained text-to-image diffusion model to synthesize new content of previously unseen regions along camera movement. However, the underlying 2D diffusion model lacks 3D awareness and results in distorted artifacts. Moreover, they are limited to generating views of static 3D scenes, neglecting to capture object movements within the dynamic 4D world. To alleviate these issues, we present DreamJourney, a two-stage framework that leverages the world simulation capacity of video diffusion models to trigger a new perpetual scene view generation task with both camera movements and object dynamics. Specifically, in stage I, DreamJourney first lifts the input image to 3D point cloud and renders a sequence of partial images from a specific camera trajectory. A video diffusion model is then utilized as generative prior to complete the missing regions and enhance visual coherence across the sequence, producing a cross-view consistent video adheres to the 3D scene and camera trajectory. Meanwhile, we introduce two simple yet effective strategies (early stopping and view padding) to further stabilize the generation process and improve visual quality. Next, in stage II, DreamJourney leverages a multimodal large language model to produce a text prompt describing object movements in current view, and uses video diffusion model to animate current view with object movements. Stage I and II are repeated recurrently, enabling perpetual dynamic scene view generation. Extensive experiments demonstrate the superiority of our DreamJourney over state-of-the-art methods both quantitatively and qualitatively. Our project page: https://dream-journey.vercel.app. |
| 5 | Dive3D: Diverse Distillation-based Text-to-3D Generation via Score Implicit Matching | 2025-06-16 | 展开Distilling pre-trained 2D diffusion models into 3D assets has driven remarkable advances in text-to-3D synthesis. However, existing methods typically rely on Score Distillation Sampling (SDS) loss, which involves asymmetric KL divergence--a formulation that inherently favors mode-seeking behavior and limits generation diversity. In this paper, we introduce Dive3D, a novel text-to-3D generation framework that replaces KL-based objectives with Score Implicit Matching (SIM) loss, a score-based objective that effectively mitigates mode collapse. Furthermore, Dive3D integrates both diffusion distillation and reward-guided optimization under a unified divergence perspective. Such reformulation, together with SIM loss, yields significantly more diverse 3D outputs while improving text alignment, human preference, and overall visual fidelity. We validate Dive3D across various 2D-to-3D prompts and find that it consistently outperforms prior methods in qualitative assessments, including diversity, photorealism, and aesthetic appeal. We further evaluate its performance on the GPTEval3D benchmark, comparing against nine state-of-the-art baselines. Dive3D also achieves strong results on quantitative metrics, including text-asset alignment, 3D plausibility, text-geometry consistency, texture quality, and geometric detail. |
| 6 | TexTailor: Customized Text-aligned Texturing via Effective Resampling | 2025-06-12 | 展开We present TexTailor, a novel method for generating consistent object textures from textual descriptions. Existing text-to-texture synthesis approaches utilize depth-aware diffusion models to progressively generate images and synthesize textures across predefined multiple viewpoints. However, these approaches lead to a gradual shift in texture properties across viewpoints due to (1) insufficient integration of previously synthesized textures at each viewpoint during the diffusion process and (2) the autoregressive nature of the texture synthesis process. Moreover, the predefined selection of camera positions, which does not account for the object's geometry, limits the effective use of texture information synthesized from different viewpoints, ultimately degrading overall texture consistency. In TexTailor, we address these issues by (1) applying a resampling scheme that repeatedly integrates information from previously synthesized textures within the diffusion process, and (2) fine-tuning a depth-aware diffusion model on these resampled textures. During this process, we observed that using only a few training images restricts the model's original ability to generate high-fidelity images aligned with the conditioning, and therefore propose an performance preservation loss to mitigate this issue. Additionally, we improve the synthesis of view-consistent textures by adaptively adjusting camera positions based on the object's geometry. Experiments on a subset of the Objaverse dataset and the ShapeNet car dataset demonstrate that TexTailor outperforms state-of-the-art methods in synthesizing view-consistent textures. The source code for TexTailor is available at https://github.com/Adios42/Textailor |
| 7 | EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence | 2025-06-12 | 展开Constructing a physically realistic and accurately scaled simulated 3D world is crucial for the training and evaluation of embodied intelligence tasks. The diversity, realism, low cost accessibility and affordability of 3D data assets are critical for achieving generalization and scalability in embodied AI. However, most current embodied intelligence tasks still rely heavily on traditional 3D computer graphics assets manually created and annotated, which suffer from high production costs and limited realism. These limitations significantly hinder the scalability of data driven approaches. We present EmbodiedGen, a foundational platform for interactive 3D world generation. It enables the scalable generation of high-quality, controllable and photorealistic 3D assets with accurate physical properties and real-world scale in the Unified Robotics Description Format (URDF) at low cost. These assets can be directly imported into various physics simulation engines for fine-grained physical control, supporting downstream tasks in training and evaluation. EmbodiedGen is an easy-to-use, full-featured toolkit composed of six key modules: Image-to-3D, Text-to-3D, Texture Generation, Articulated Object Generation, Scene Generation and Layout Generation. EmbodiedGen generates diverse and interactive 3D worlds composed of generative 3D assets, leveraging generative AI to address the challenges of generalization and evaluation to the needs of embodied intelligence related research. Code is available at https://horizonrobotics.github.io/robot_lab/embodied_gen/index.html. |
| 8 | DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision | 2025-06-11 | 展开While text-to-3D generation has attracted growing interest, existing methods often struggle to produce 3D assets that align well with human preferences. Current preference alignment techniques for 3D content typically rely on hardly-collected preference-paired multi-view 2D images to train 2D reward models, when then guide 3D generation -- leading to geometric artifacts due to their inherent 2D bias. To address these limitations, we construct 3D-MeshPref, the first large-scale unpaired 3D preference dataset, featuring diverse 3D meshes annotated by a large language model and refined by human evaluators. We then develop RewardCS, the first reward model trained directly on unpaired 3D-MeshPref data using a novel Cauchy-Schwarz divergence objective, enabling effective learning of human-aligned 3D geometric preferences without requiring paired comparisons. Building on this, we propose DreamCS, a unified framework that integrates RewardCS into text-to-3D pipelines -- enhancing both implicit and explicit 3D generation with human preference feedback. Extensive experiments show DreamCS outperforms prior methods, producing 3D assets that are both geometrically faithful and human-preferred. Code and models will be released publicly. |
| 9 | R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation | 2025-06-09 | 展开Validating autonomous driving (AD) systems requires diverse and safety-critical testing, making photorealistic virtual environments essential. Traditional simulation platforms, while controllable, are resource-intensive to scale and often suffer from a domain gap with real-world data. In contrast, neural reconstruction methods like 3D Gaussian Splatting (3DGS) offer a scalable solution for creating photorealistic digital twins of real-world driving scenes. However, they struggle with dynamic object manipulation and reusability as their per-scene optimization-based methodology tends to result in incomplete object models with integrated illumination effects. This paper introduces R3D2, a lightweight, one-step diffusion model designed to overcome these limitations and enable realistic insertion of complete 3D assets into existing scenes by generating plausible rendering effects-such as shadows and consistent lighting-in real time. This is achieved by training R3D2 on a novel dataset: 3DGS object assets are generated from in-the-wild AD data using an image-conditioned 3D generative model, and then synthetically placed into neural rendering-based virtual environments, allowing R3D2 to learn realistic integration. Quantitative and qualitative evaluations demonstrate that R3D2 significantly enhances the realism of inserted assets, enabling use-cases like text-to-3D asset insertion and cross-scene/dataset object transfer, allowing for true scalability in AD validation. To promote further research in scalable and realistic AD simulation, we will release our dataset and code, see https://research.zenseact.com/publications/R3D2/. |
| 10 | AI-powered Contextual 3D Environment Generation: A Systematic Review | 2025-06-05 | 展开The generation of high-quality 3D environments is crucial for industries such as gaming, virtual reality, and cinema, yet remains resource-intensive due to the reliance on manual processes. This study performs a systematic review of existing generative AI techniques for 3D scene generation, analyzing their characteristics, strengths, limitations, and potential for improvement. By examining state-of-the-art approaches, it presents key challenges such as scene authenticity and the influence of textual inputs. Special attention is given to how AI can blend different stylistic domains while maintaining coherence, the impact of training data on output quality, and the limitations of current models. In addition, this review surveys existing evaluation metrics for assessing realism and explores how industry professionals incorporate AI into their workflows. The findings of this study aim to provide a comprehensive understanding of the current landscape and serve as a foundation for future research on AI-driven 3D content generation. Key findings include that advanced generative architectures enable high-quality 3D content creation at a high computational cost, effective multi-modal integration techniques like cross-attention and latent space alignment facilitate text-to-3D tasks, and the quality and diversity of training data combined with comprehensive evaluation metrics are critical to achieving scalable, robust 3D scene generation. |
| 11 | CzechLynx: A Dataset for Individual Identification and Pose Estimation of the Eurasian Lynx | 2025-06-05 | 展开We introduce CzechLynx, the first large-scale, open-access dataset for individual identification, 2D pose estimation, and instance segmentation of the Eurasian lynx (Lynx lynx). CzechLynx includes more than 30k camera trap images annotated with segmentation masks, identity labels, and 20-point skeletons and covers 219 unique individuals across 15 years of systematic monitoring in two geographically distinct regions: Southwest Bohemia and the Western Carpathians. To increase the data variability, we create a complementary synthetic set with more than 100k photorealistic images generated via a Unity-based pipeline and diffusion-driven text-to-texture modeling, covering diverse environments, poses, and coat-pattern variations. To allow testing generalization across spatial and temporal domains, we define three tailored evaluation protocols/splits: (i) geo-aware, (ii) time-aware open-set, and (iii) time-aware closed-set. This dataset is targeted to be instrumental in benchmarking state-of-the-art models and the development of novel methods for not just individual animal re-identification. |
| 12 | Unify3D: An Augmented Holistic End-to-end Monocular 3D Human Reconstruction via Anatomy Shaping and Twins Negotiating | 2025-04-25 | 展开Monocular 3D clothed human reconstruction aims to create a complete 3D avatar from a single image. To tackle the human geometry lacking in one RGB image, current methods typically resort to a preceding model for an explicit geometric representation. For the reconstruction itself, focus is on modeling both it and the input image. This routine is constrained by the preceding model, and overlooks the integrity of the reconstruction task. To address this, this paper introduces a novel paradigm that treats human reconstruction as a holistic process, utilizing an end-to-end network for direct prediction from 2D image to 3D avatar, eliminating any explicit intermediate geometry display. Based on this, we further propose a novel reconstruction framework consisting of two core components: the Anatomy Shaping Extraction module, which captures implicit shape features taking into account the specialty of human anatomy, and the Twins Negotiating Reconstruction U-Net, which enhances reconstruction through feature interaction between two U-Nets of different modalities. Moreover, we propose a Comic Data Augmentation strategy and construct 15k+ 3D human scans to bolster model performance in more complex case input. Extensive experiments on two test sets and many in-the-wild cases show the superiority of our method over SOTA methods. Our demos can be found in : https://e2e3dgsrecon.github.io/e2e3dgsrecon/. |
| 13 | CasTex: Cascaded Text-to-Texture Synthesis via Explicit Texture Maps and Physically-Based Shading | 2025-04-09 | 展开This work investigates text-to-texture synthesis using diffusion models to generate physically-based texture maps. We aim to achieve realistic model appearances under varying lighting conditions. A prominent solution for the task is score distillation sampling. It allows recovering a complex texture using gradient guidance given a differentiable rasterization and shading pipeline. However, in practice, the aforementioned solution in conjunction with the widespread latent diffusion models produces severe visual artifacts and requires additional regularization such as implicit texture parameterization. As a more direct alternative, we propose an approach using cascaded diffusion models for texture synthesis (CasTex). In our setup, score distillation sampling yields high-quality textures out-of-the box. In particular, we were able to omit implicit texture parameterization in favor of an explicit parameterization to improve the procedure. In the experiments, we show that our approach significantly outperforms state-of-the-art optimization-based solutions on public texture synthesis benchmarks. |
| 14 | ProcTex: Consistent and Interactive Text-to-texture Synthesis for Procedural Models | 2025-01-28 | 展开Recent advancement in 2D image diffusion models has driven significant progress in text-guided texture synthesis, enabling realistic, high-quality texture generation from arbitrary text prompts. However, current methods usually focus on synthesizing texture for single static 3D objects, and struggle to handle entire families of shapes, such as those produced by procedural programs. Applying existing methods naively to each procedural shape is too slow to support exploring different parameter settings at interactive rates, and also results in inconsistent textures across the procedural shapes. To this end, we introduce ProcTex, the first text-to-texture system designed for procedural 3D models. ProcTex enables consistent and real-time text-guided texture synthesis for families of shapes, which integrates seamlessly with the interactive design flow of procedural models. To ensure consistency, our core approach is to generate texture for the shape produced by one setting of the procedural parameters, followed by a texture transfer stage to apply the texture to other parameter settings. We also develop several techniques, including a novel UV displacement network for real-time texture transfer, the retexturing pipeline to support structural changes from discrete procedural parameters, and part-level UV texture map generation for local appearance editing. Extensive experiments on a diverse set of professional procedural models validate ProcTex's ability to produce high-quality, visually consistent textures while supporting real-time, interactive applications. |
| 15 | Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction | 2024-11-21 | 展开Existing feedforward image-to-3D methods mainly rely on 2D multi-view diffusion models that cannot guarantee 3D consistency. These methods easily collapse when changing the prompt view direction and mainly handle object-centric cases. In this paper, we propose a novel single-stage 3D diffusion model, DiffusionGS, for object generation and scene reconstruction from a single view. DiffusionGS directly outputs 3D Gaussian point clouds at each timestep to enforce view consistency and allow the model to generate robustly given prompt views of any directions, beyond object-centric inputs. Plus, to improve the capability and generality of DiffusionGS, we scale up 3D training data by developing a scene-object mixed training strategy. Experiments show that DiffusionGS yields improvements of 2.20 dB/23.25 and 1.34 dB/19.16 in PSNR/FID for objects and scenes than the state-of-the-art methods, without depth estimator. Plus, our method enjoys over 5$\times$ faster speed ($\sim$6s on an A100 GPU). Our Project page at https://caiyuanhao1998.github.io/project/DiffusionGS/ shows the video and interactive results. |
| 16 | MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D | 2024-11-04 | 展开Texturing is a crucial step in the 3D asset production workflow, which enhances the visual appeal and diversity of 3D assets. Despite recent advancements in Text-to-Texture (T2T) generation, existing methods often yield subpar results, primarily due to local discontinuities, inconsistencies across multiple views, and their heavy dependence on UV unwrapping outcomes. To tackle these challenges, we propose a novel generation-refinement 3D texturing framework called MVPaint, which can generate high-resolution, seamless textures while emphasizing multi-view consistency. MVPaint mainly consists of three key modules. 1) Synchronized Multi-view Generation (SMG). Given a 3D mesh model, MVPaint first simultaneously generates multi-view images by employing an SMG model, which leads to coarse texturing results with unpainted parts due to missing observations. 2) Spatial-aware 3D Inpainting (S3I). To ensure complete 3D texturing, we introduce the S3I method, specifically designed to effectively texture previously unobserved areas. 3) UV Refinement (UVR). Furthermore, MVPaint employs a UVR module to improve the texture quality in the UV space, which first performs a UV-space Super-Resolution, followed by a Spatial-aware Seam-Smoothing algorithm for revising spatial texturing discontinuities caused by UV unwrapping. Moreover, we establish two T2T evaluation benchmarks: the Objaverse T2T benchmark and the GSO T2T benchmark, based on selected high-quality 3D meshes from the Objaverse dataset and the entire GSO dataset, respectively. Extensive experimental results demonstrate that MVPaint surpasses existing state-of-the-art methods. Notably, MVPaint could generate high-fidelity textures with minimal Janus issues and highly enhanced cross-view consistency. |
| 17 | SceneComplete: Open-World 3D Scene Completion in Cluttered Real World Environments for Robot Manipulation | 2024-10-31 | 展开Careful robot manipulation in every-day cluttered environments requires an accurate understanding of the 3D scene, in order to grasp and place objects stably and reliably and to avoid colliding with other objects. In general, we must construct such a 3D interpretation of a complex scene based on limited input, such as a single RGB-D image. We describe SceneComplete, a system for constructing a complete, segmented, 3D model of a scene from a single view. SceneComplete is a novel pipeline for composing general-purpose pretrained perception modules (vision-language, segmentation, image-inpainting, image-to-3D, visual-descriptors and pose-estimation) to obtain highly accurate results. We demonstrate its accuracy and effectiveness with respect to ground-truth models in a large benchmark dataset and show that its accurate whole-object reconstruction enables robust grasp proposal generation, including for a dexterous hand. We release the code on our website https://scenecomplete.github.io/. |
| 18 | 3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation | 2024-10-24 | 展开Multi-view image diffusion models have significantly advanced open-domain 3D object generation. However, most existing models rely on 2D network architectures that lack inherent 3D biases, resulting in compromised geometric consistency. To address this challenge, we introduce 3D-Adapter, a plug-in module designed to infuse 3D geometry awareness into pretrained image diffusion models. Central to our approach is the idea of 3D feedback augmentation: for each denoising step in the sampling loop, 3D-Adapter decodes intermediate multi-view features into a coherent 3D representation, then re-encodes the rendered RGBD views to augment the pretrained base model through feature addition. We study two variants of 3D-Adapter: a fast feed-forward version based on Gaussian splatting and a versatile training-free version utilizing neural fields and meshes. Our extensive experiments demonstrate that 3D-Adapter not only greatly enhances the geometry quality of text-to-multi-view models such as Instant3D and Zero123++, but also enables high-quality 3D generation using the plain text-to-image Stable Diffusion. Furthermore, we showcase the broad application potential of 3D-Adapter by presenting high quality results in text-to-3D, image-to-3D, text-to-texture, and text-to-avatar tasks. |
| 19 | Jointly Generating Multi-view Consistent PBR Textures using Collaborative Control | 2024-10-09 | 展开Multi-view consistency remains a challenge for image diffusion models. Even within the Text-to-Texture problem, where perfect geometric correspondences are known a priori, many methods fail to yield aligned predictions across views, necessitating non-trivial fusion methods to incorporate the results onto the original mesh. We explore this issue for a Collaborative Control workflow specifically in PBR Text-to-Texture. Collaborative Control directly models PBR image probability distributions, including normal bump maps; to our knowledge, the only diffusion model to directly output full PBR stacks. We discuss the design decisions involved in making this model multi-view consistent, and demonstrate the effectiveness of our approach in ablation studies, as well as practical applications. |
| 20 | FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving | 2024-08-13 | 展开The integration of data from diverse sensor modalities (e.g., camera and LiDAR) constitutes a prevalent methodology within the ambit of autonomous driving scenarios. Recent advancements in efficient point cloud transformers have underscored the efficacy of integrating information in sparse formats. When it comes to fusion, since image patches are dense in pixel space with ambiguous depth, it necessitates additional design considerations for effective fusion. In this paper, we conduct a comprehensive exploration of design choices for Transformer-based sparse cameraLiDAR fusion. This investigation encompasses strategies for image-to-3D and LiDAR-to-2D mapping, attention neighbor grouping, single modal tokenizer, and micro-structure of Transformer. By amalgamating the most effective principles uncovered through our investigation, we introduce FlatFusion, a carefully designed framework for sparse camera-LiDAR fusion. Notably, FlatFusion significantly outperforms state-of-the-art sparse Transformer-based methods, including UniTR, CMT, and SparseFusion, achieving 73.7 NDS on the nuScenes validation set with 10.1 FPS with PyTorch. |
| 21 | SceneMotifCoder: Example-driven Visual Program Learning for Generating 3D Object Arrangements | 2024-08-05 | 展开Despite advances in text-to-3D generation methods, generation of multi-object arrangements remains challenging. Current methods exhibit failures in generating physically plausible arrangements that respect the provided text description. We present SceneMotifCoder (SMC), an example-driven framework for generating 3D object arrangements through visual program learning. SMC leverages large language models (LLMs) and program synthesis to overcome these challenges by learning visual programs from example arrangements. These programs are generalized into compact, editable meta-programs. When combined with 3D object retrieval and geometry-aware optimization, they can be used to create object arrangements varying in arrangement structure and contained objects. Our experiments show that SMC generates high-quality arrangements using meta-programs learned from few examples. Evaluation results demonstrates that object arrangements generated by SMC better conform to user-specified text descriptions and are more physically plausible when compared with state-of-the-art text-to-3D generation and layout methods. |
| 22 | LLM2TEA: Agentic AI Designer Finds Innovative Objects with Generative Evolutionary Multitasking | 2024-06-21 | 展开In this paper, we introduce LLM-driven MultiTask Evolutionary Algorithm (LLM2TEA), the first agentic AI designer within a generative evolutionary multitasking (GEM) framework that promotes the crossover and synergy of designs from multiple domains, leading to innovative solutions that transcend individual disciplines. Of particular interest is the discovery of objects that are not only innovative but also conform to the physical specifications of the real world in science and engineering. LLM2TEA comprises a large language model to initialize a population of genotypes (defined by text prompts) describing the objects of interest, a text-to-3D generative model to produce phenotypes from these prompts, a classifier to interpret the semantic representations of the objects, and a physics simulation model to assess their physical properties. We propose several novel LLM-based multitask evolutionary operators to guide the search toward the discovery of high-performing practical objects. Experimental results in conceptual design optimization validate the effectiveness of LLM2TEA, revealing from 97% to 174% improvement in the diversity of innovative objects compared to the present text-to-3D generative model baseline. In addition, more than 73% of the generated designs have better physical performance than the top 1% percentile of the designs generated in the baseline. Moreover, LLM2TEA generates designs that are not only aesthetically creative but also functional in real-world applications. Several of these designs have been successfully 3D-printed, emphasizing the proposed approach's capacity to transform AI-generated outputs into tangible physical objects. The designs produced by LLM2TEA meets practical requirements while showcasing creative and innovative features, underscoring its potential applications in complex design optimization and discovery. |
| 23 | FlashTex: Fast Relightable Mesh Texturing with LightControlNet | 2024-02-20 | 展开Manually creating textures for 3D meshes is time-consuming, even for expert visual content creators. We propose a fast approach for automatically texturing an input 3D mesh based on a user-provided text prompt. Importantly, our approach disentangles lighting from surface material/reflectance in the resulting texture so that the mesh can be properly relit and rendered in any lighting environment. We introduce LightControlNet, a new text-to-image model based on the ControlNet architecture, which allows the specification of the desired lighting as a conditioning image to the model. Our text-to-texture pipeline then constructs the texture in two stages. The first stage produces a sparse set of visually consistent reference views of the mesh using LightControlNet. The second stage applies a texture optimization based on Score Distillation Sampling (SDS) that works with LightControlNet to increase the texture quality while disentangling surface material from lighting. Our algorithm is significantly faster than previous text-to-texture methods, while producing high-quality and relightable textures. |
| 序号 | 标题 | 日期 | 摘要 |
|---|---|---|---|
| 1 | A Survey on Vision-Language-Action Models for Autonomous Driving | 2025-06-30 | 展开The rapid progress of multimodal large language models (MLLM) has paved the way for Vision-Language-Action (VLA) paradigms, which integrate visual perception, natural language understanding, and control within a single policy. Researchers in autonomous driving are actively adapting these methods to the vehicle domain. Such models promise autonomous vehicles that can interpret high-level instructions, reason about complex traffic scenes, and make their own decisions. However, the literature remains fragmented and is rapidly expanding. This survey offers the first comprehensive overview of VLA for Autonomous Driving (VLA4AD). We (i) formalize the architectural building blocks shared across recent work, (ii) trace the evolution from early explainer to reasoning-centric VLA models, and (iii) compare over 20 representative models according to VLA's progress in the autonomous driving domain. We also consolidate existing datasets and benchmarks, highlighting protocols that jointly measure driving safety, accuracy, and explanation quality. Finally, we detail open challenges - robustness, real-time efficiency, and formal verification - and outline future directions of VLA4AD. This survey provides a concise yet complete reference for advancing interpretable socially aligned autonomous vehicles. Github repo is available at \href{https://github.com/JohnsonJiang1996/Awesome-VLA4AD}{SicongJiang/Awesome-VLA4AD}. |
| 2 | What Challenges Do Developers Face When Using Verification-Aware Programming Languages? | 2025-06-30 | 展开Software reliability is critical in ensuring that the digital systems we depend on function correctly. In software development, increasing software reliability often involves testing. However, for complex and critical systems, developers can use Design by Contract (DbC) methods to define precise specifications that software components must satisfy. Verification-Aware (VA) programming languages support DbC and formal verification at compile-time or run-time, offering stronger correctness guarantees than traditional testing. However, despite the strong guarantees provided by VA languages, their adoption remains limited. In this study, we investigate the barriers to adopting VA languages by analyzing developer discussions on public forums using topic modeling techniques. We complement this analysis with a developer survey to better understand the practical challenges associated with VA languages. Our findings reveal key obstacles to adoption, including steep learning curves and usability issues. Based on these insights, we identify actionable recommendations to improve the usability and accessibility of VA languages. Our findings suggest that simplifying tool interfaces, providing better educational materials, and improving integration with everyday development environments could improve the usability and adoption of these languages. Our work provides actionable insights for improving the usability of VA languages and making verification tools more accessible. |
| 3 | Universal Gluing and Contextual Choice: Categorical Logic and the Foundations of Analytic Approximation | 2025-06-28 | 展开We introduce a new categorical and constructive foundation for analytic approximation based on a Contextual Choice Principle (CCP), which enforces locality and compatibility in the construction of mathematical objects. Central to our approach is the Universal Embedding and Linear Approximation Theorem (UELAT), which establishes that functions in broad spaces -- including C(K), Sobolev spaces W^{k,p}(Omega), and distributions D'(Omega) -- can be explicitly approximated by finite-rank linear projections, each with a constructive, algorithmically verifiable certificate of accuracy. These constructions are governed categorically by a functorial adjunction between local logical probes and analytic models, making analytic existence both formally certifiable and programmatically extractable. As a key result, we prove a uniform certificate stability theorem, ensuring that approximation certificates persist under uniform convergence. The CCP avoids classical pathologies (e.g., non-measurable sets, Banach--Tarski paradoxes) by eliminating non-constructive choice and replacing it with a coherent, local-to-global semantic logic. Our framework strengthens the foundations of constructive analysis while contributing tools relevant to formal verification, type-theoretic proof systems, and computational mathematics. |
| 4 | Can Large Language Models Help Students Prove Software Correctness? An Experimental Study with Dafny | 2025-06-27 | 展开Students in computing education increasingly use large language models (LLMs) such as ChatGPT. Yet, the role of LLMs in supporting cognitively demanding tasks, like deductive program verification, remains poorly understood. This paper investigates how students interact with an LLM when solving formal verification exercises in Dafny, a language that supports functional correctness, by allowing programmers to write formal specifications and automatically verifying that the implementation satisfies the specification. We conducted a mixed-methods study with master's students enrolled in a formal methods course. Each participant completed two verification problems, one with access to a custom ChatGPT interface that logged all interactions, and the other without. We identified strategies used by successful students and assessed the level of trust students place in LLMs. Our findings show that students perform significantly better when using ChatGPT; however, performance gains are tied to prompt quality. We conclude with practical recommendations for integrating LLMs into formal methods courses more effectively, including designing LLM-aware challenges that promote learning rather than substitution. |
| 5 | Diophantine Equations over $\mathbb Z$: Universal Bounds and Parallel Formalization | 2025-06-26 | 展开This paper explores multiple closely related themes: bounding the complexity of Diophantine equations over the integers and developing mathematical proofs in parallel with formal theorem provers. Hilbert's Tenth Problem (H10) asks about the decidability of Diophantine equations and has been answered negatively by Davis, Putnam, Robinson and Matiyasevich. It is natural to ask for which subclasses of Diophantine equations H10 remains undecidable. Such subclasses can be defined in terms of universal pairs: bounds on the number of variables |
| 6 | The Composition of Digital Twins for Systems-of-Systems: a Systematic Literature Review | 2025-06-25 | 展开Digital Twins (DTs) are increasingly used to model complex systems, especially in Cyber-Physical Systems (CPS) and System-of-Systems (SoS), where effective integration is key. This systematic literature review investigates DT composition and verification and validation (V&V) methodologies. Analyzing 21 studies from 2022-2024, we examined composition mechanisms, SoS characteristics, and V&V formality, scope, and challenges. While composition is discussed, formalization is limited. V&V approaches vary, with semi-formal methods and simulations dominating; formal verification is underutilized. Key technical challenges include model uncertainty and integration complexity. Methodological challenges highlight the lack of standardized DT-specific V&V frameworks. There is a need to move beyond model validation to address integration and cyber-physical consistency. This review contributes a structured classification of V&V approaches and emphasizes the need for standardized, scalable V&V and rigorous composition methodologies for complex DT implementations. |
| 7 | Prover Agent: An Agent-based Framework for Formal Mathematical Proofs | 2025-06-24 | 展开We present Prover Agent, a novel AI agent for automated theorem proving that integrates large language models (LLMs) with a formal proof assistant, Lean. Prover Agent coordinates an informal reasoning LLM, a formal prover model, and feedback from Lean while also generating auxiliary lemmas to assist in discovering the overall proof strategy. It achieves an 86.1% success rate on the MiniF2F benchmark, establishing a new state-of-the-art among methods using small language models (SLMs) with a much lower sample budget than previous approaches. We also present case studies illustrating how these generated lemmas contribute to solving challenging problems. |
| 8 | Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models | 2025-06-13 | 展开Recent advancements, such as DeepSeek-Prover-V2-671B and Kimina-Prover-Preview-72B, demonstrate a prevailing trend in leveraging reinforcement learning (RL)-based large-scale training for automated theorem proving. Surprisingly, we discover that even without any training, careful neuro-symbolic coordination of existing off-the-shelf reasoning models and tactic step provers can achieve comparable performance. This paper introduces \textbf{DSP+}, an improved version of the Draft, Sketch, and Prove framework, featuring a \emph{fine-grained and integrated} neuro-symbolic enhancement for each phase: (1) In the draft phase, we prompt reasoning models to generate concise natural-language subgoals to benefit the sketch phase, removing thinking tokens and references to human-written proofs; (2) In the sketch phase, subgoals are autoformalized with hypotheses to benefit the proving phase, and sketch lines containing syntactic errors are masked according to predefined rules; (3) In the proving phase, we tightly integrate symbolic search methods like Aesop with step provers to establish proofs for the sketch subgoals. Experimental results show that, without any additional model training or fine-tuning, DSP+ solves 80.7%, 32.8%, and 24 out of 644 problems from miniF2F, ProofNet, and PutnamBench, respectively, while requiring fewer budgets compared to state-of-the-arts. DSP+ proves \texttt{imo_2019_p1}, an IMO problem in miniF2F that is not solved by any prior work. Additionally, DSP+ generates proof patterns comprehensible by human experts, facilitating the identification of formalization errors; For example, eight wrongly formalized statements in miniF2F are discovered. Our results highlight the potential of classical reasoning patterns besides the RL-based training. All components will be open-sourced. |
| 9 | StepProof: Step-by-step verification of natural language mathematical proofs | 2025-06-12 | 展开Interactive theorem provers (ITPs) are powerful tools for the formal verification of mathematical proofs down to the axiom level. However, their lack of a natural language interface remains a significant limitation. Recent advancements in large language models (LLMs) have enhanced the understanding of natural language inputs, paving the way for autoformalization - the process of translating natural language proofs into formal proofs that can be verified. Despite these advancements, existing autoformalization approaches are limited to verifying complete proofs and lack the capability for finer, sentence-level verification. To address this gap, we propose StepProof, a novel autoformalization method designed for granular, step-by-step verification. StepProof breaks down complete proofs into multiple verifiable subproofs, enabling sentence-level verification. Experimental results demonstrate that StepProof significantly improves proof success rates and efficiency compared to traditional methods. Additionally, we found that minor manual adjustments to the natural language proofs, tailoring them for step-level verification, further enhanced StepProof's performance in autoformalization. |
| 10 | The Alignment Trap: Complexity Barriers | 2025-06-12 | 展开This paper argues that AI alignment is not merely difficult, but is founded on a fundamental logical contradiction. We first establish The Enumeration Paradox: we use machine learning precisely because we cannot enumerate all necessary safety rules, yet making ML safe requires examples that can only be generated from the very enumeration we admit is impossible. This paradox is then confirmed by a set of five independent mathematical proofs, or "pillars of impossibility." Our main results show that: (1) Geometric Impossibility: The set of safe policies has measure zero, a necessary consequence of projecting infinite-dimensional world-context requirements onto finite-dimensional models. (2) Computational Impossibility: Verifying a policy's safety is coNP-complete, even for non-zero error tolerances. (3) Statistical Impossibility: The training data required for safety (abundant examples of rare disasters) is a logical contradiction and thus unobtainable. (4) Information-Theoretic Impossibility: Safety rules contain more incompressible, arbitrary information than any feasible network can store. (5) Dynamic Impossibility: The optimization process for increasing AI capability is actively hostile to safety, as the gradients for the two objectives are generally anti-aligned. Together, these results demonstrate that the pursuit of safe, highly capable AI is not a matter of overcoming technical hurdles, but of confronting fundamental, interlocking barriers. The paper concludes by presenting a strategic trilemma that these impossibilities force upon the field. A formal verification of the core theorems in Lean4 is currently in progress. |
| 11 | MATP-BENCH: Can MLLM Be a Good Automated Theorem Prover for Multimodal Problems? | 2025-06-06 | 展开Numerous theorems, such as those in geometry, are often presented in multimodal forms (e.g., diagrams). Humans benefit from visual reasoning in such settings, using diagrams to gain intuition and guide the proof process. Modern Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in solving a wide range of mathematical problems. However, the potential of MLLMs as Automated Theorem Provers (ATPs), specifically in the multimodal domain, remains underexplored. In this paper, we introduce the Multimodal Automated Theorem Proving benchmark (MATP-BENCH), a new Multimodal, Multi-level, and Multi-language benchmark designed to evaluate MLLMs in this role as multimodal automated theorem provers. MATP-BENCH consists of 1056 multimodal theorems drawn from high school, university, and competition-level mathematics. All these multimodal problems are accompanied by formalizations in Lean 4, Coq and Isabelle, thus making the benchmark compatible with a wide range of theorem-proving frameworks. MATP-BENCH requires models to integrate sophisticated visual understanding with mastery of a broad spectrum of mathematical knowledge and rigorous symbolic reasoning to generate formal proofs. We use MATP-BENCH to evaluate a variety of advanced multimodal language models. Existing methods can only solve a limited number of the MATP-BENCH problems, indicating that this benchmark poses an open challenge for research on automated theorem proving. |
| 12 | ProofNet++: A Neuro-Symbolic System for Formal Proof Verification with Self-Correction | 2025-05-30 | 展开We propose ProofNet++, a neuro-symbolic framework that enhances automated theorem proving by combining large language models (LLMs) with formal proof verification and self-correction mechanisms. Current LLM-based systems suffer from hallucinated logical steps and unverifiable reasoning. ProofNet++ mitigates these limitations by integrating symbolic proof tree supervision, a reinforcement learning loop using verifiers as reward functions, and an iterative self-correction module. Our experiments on miniF2F, Lean's mathlib, and HOL Light show that ProofNet++ significantly improves proof accuracy, correctness, and formal verifiability over prior models. We provide theoretical analysis of the convergence and stability of the verifier-guided RL framework and release our datasets and codebase for future research. |
| 13 | DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning | 2025-05-29 | 展开Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approaches rely heavily on formal proof systems that poorly align with LLMs' strength derived from informal, natural language knowledge acquired during pre-training. In this work, we propose DeepTheorem, a comprehensive informal theorem-proving framework exploiting natural language to enhance LLM mathematical reasoning. DeepTheorem includes a large-scale benchmark dataset consisting of 121K high-quality IMO-level informal theorems and proofs spanning diverse mathematical domains, rigorously annotated for correctness, difficulty, and topic categories, accompanied by systematically constructed verifiable theorem variants. We devise a novel reinforcement learning strategy (RL-Zero) explicitly tailored to informal theorem proving, leveraging the verified theorem variants to incentivize robust mathematical inference. Additionally, we propose comprehensive outcome and process evaluation metrics examining proof correctness and the quality of reasoning steps. Extensive experimental analyses demonstrate DeepTheorem significantly improves LLM theorem-proving performance compared to existing datasets and supervised fine-tuning protocols, achieving state-of-the-art accuracy and reasoning quality. Our findings highlight DeepTheorem's potential to fundamentally advance automated informal theorem proving and mathematical exploration. |
| 14 | Autoformalization in the Era of Large Language Models: A Survey | 2025-05-29 | 展开Autoformalization, the process of transforming informal mathematical propositions into verifiable formal representations, is a foundational task in automated theorem proving, offering a new perspective on the use of mathematics in both theoretical and applied domains. Driven by the rapid progress in artificial intelligence, particularly large language models (LLMs), this field has witnessed substantial growth, bringing both new opportunities and unique challenges. In this survey, we provide a comprehensive overview of recent advances in autoformalization from both mathematical and LLM-centric perspectives. We examine how autoformalization is applied across various mathematical domains and levels of difficulty, and analyze the end-to-end workflow from data preprocessing to model design and evaluation. We further explore the emerging role of autoformalization in enhancing the verifiability of LLM-generated outputs, highlighting its potential to improve both the trustworthiness and reasoning capabilities of LLMs. Finally, we summarize key open-source models and datasets supporting current research, and discuss open challenges and promising future directions for the field. |
| 15 | Automated Discovery of Tactic Libraries for Interactive Theorem Proving | 2025-03-31 | 展开Enabling more concise and modular proofs is essential for advancing formal reasoning using interactive theorem provers (ITPs). Since many ITPs, such as Rocq and Lean, use tactic-style proofs, learning higher-level custom tactics is crucial for proof modularity and automation. This paper presents a novel approach to tactic discovery, which leverages Tactic Dependence Graphs (TDGs) to identify reusable proof strategies across multiple proofs. TDGs capture logical dependencies between tactic applications while abstracting away irrelevant syntactic details, allowing for both the discovery of new tactics and the refactoring of existing proofs into more modular forms. We have implemented this technique in a tool called TacMiner and compare it against an anti-unification-based approach Peano to tactic discovery. Our evaluation demonstrates that TacMiner can learn 3x as many tactics as Peano and reduces the size of proofs by 26% across all benchmarks. Furthermore, our evaluation demonstrates the benefits of learning custom tactics for proof automation, allowing a state-of-the-art proof automation tool to achieve a relative increase of 172% in terms of success rate. |
| 16 | Local Look-Ahead Guidance via Verifier-in-the-Loop for Automated Theorem Proving | 2025-03-12 | 展开The most promising recent methods for AI reasoning require applying variants of reinforcement learning (RL) either on rolled out trajectories from the LLMs, even for the step-wise rewards, or large quantities of human-annotated trajectory data. The reliance on the rolled-out trajectory renders the compute cost and time prohibitively high. In particular, the correctness of a reasoning trajectory can typically only be judged at its completion, leading to sparse rewards in RL or requiring expensive synthetic data generation in expert iteration-like methods. In this work, we focus on the Automatic Theorem Proving (ATP) task and propose a novel verifier-in-the-loop design, which, unlike existing approaches that leverage feedback on the entire reasoning trajectory, employs an automated verifier to give intermediate feedback at each step of the reasoning process. Using Lean as the verifier, we empirically show that the step-by-step local verification produces a global improvement in the model's reasoning accuracy and efficiency. |
| 17 | Faithful Logic Embeddings in HOL -- Deep and Shallow | 2025-02-26 | 展开Deep and shallow embeddings of non-classical logics in classical higher-order logic have been explored, implemented, and used in various reasoning tools in recent years. This paper presents a method for the simultaneous deployment of deep and shallow embeddings of various degrees in classical higher-order logic. This enables flexible, interactive and automated theorem proving and counterexample finding at meta and object level, as well as automated faithfulness proofs between these logic embeddings. The method is beneficial for logic education, research and application and is illustrated here using a simple propositional modal logic. However, this approach is conceptual in nature and not limited to this simple logic context. |
| 18 | LeanProgress: Guiding Search for Neural Theorem Proving via Proof Progress Prediction | 2025-02-25 | 展开Mathematical reasoning remains a significant challenge for Large Language Models (LLMs) due to hallucinations. When combined with formal proof assistants like Lean, these hallucinations can be eliminated through rigorous verification, making theorem proving reliable. However, even with formal verification, LLMs still struggle with long proofs and complex mathematical formalizations. While Lean with LLMs offers valuable assistance with retrieving lemmas, generating tactics, or even complete proofs, it lacks a crucial capability: providing a sense of proof progress. This limitation particularly impacts the overall development efficiency in large formalization projects. We introduce LeanProgress, a method that predicts the progress in the proof. Training and evaluating our models made on a large corpus of Lean proofs from Lean Workbook Plus and Mathlib4 and how many steps remain to complete it, we employ data preprocessing and balancing techniques to handle the skewed distribution of proof lengths. Our experiments show that LeanProgress achieves an overall prediction accuracy of 75.1% in predicting the amount of progress and, hence, the remaining number of steps. When integrated into a best-first search framework using Reprover, our method shows a 3.8% improvement on Mathlib4 compared to baseline performances of 41.2%, particularly for longer proofs. These results demonstrate how proof progress prediction can enhance both automated and interactive theorem proving, enabling users to make more informed decisions about proof strategies. |
| 19 | Proving the Coding Interview: A Benchmark for Formally Verified Code Generation | 2025-02-08 | 展开We introduce the Formally Verified Automated Programming Progress Standards, or FVAPPS, a benchmark of 4715 samples for writing programs and proving their correctness, the largest formal verification benchmark, including 1083 curated and quality controlled samples. Previously, APPS provided a benchmark and dataset for programming puzzles to be completed in Python and checked against unit tests, of the kind seen in technical assessments in the software engineering industry. Building upon recent approaches for benchmarks in interactive theorem proving, we generalize the unit tests to Lean 4 theorems given without proof (i.e., using Lean's "sorry" keyword). On the 406 theorems of 100 randomly selected samples, Sonnet correctly proves 30% and Gemini correctly proves 18%. We challenge the machine learning and program synthesis communities to solve both each general purpose programming problem and its associated correctness specifications. The benchmark is available at https://huggingface.co/datasets/quinn-dougherty/fvapps. |
| 20 | Learning Rules Explaining Interactive Theorem Proving Tactic Prediction | 2024-11-02 | 展开Formally verifying the correctness of mathematical proofs is more accessible than ever, however, the learning curve remains steep for many of the state-of-the-art interactive theorem provers (ITP). Deriving the most appropriate subsequent proof step, and reasoning about it, given the multitude of possibilities, remains a daunting task for novice users. To improve the situation, several investigations have developed machine learning based guidance for tactic selection. Such approaches struggle to learn non-trivial relationships between the chosen tactic and the structure of the proof state and represent them as symbolic expressions. To address these issues we (i) We represent the problem as an Inductive Logic Programming (ILP) task, (ii) Using the ILP representation we enriched the feature space by encoding additional, computationally expensive properties as background knowledge predicates, (iii) We use this enriched feature space to learn rules explaining when a tactic is applicable to a given proof state, (iv) we use the learned rules to filter the output of an existing tactic selection approach and empirically show improvement over the non-filtering approaches. |
| 21 | Tableaux for Automated Reasoning in Dependently-Typed Higher-Order Logic (Extended Version) | 2024-10-18 | 展开Dependent type theory gives an expressive type system facilitating succinct formalizations of mathematical concepts. In practice, it is mainly used for interactive theorem proving with intensional type theories, with PVS being a notable exception. In this paper, we present native rules for automated reasoning in a dependently-typed version (DHOL) of classical higher-order logic (HOL). DHOL has an extensional type theory with an undecidable type checking problem which contains theorem proving. We implemented the inference rules as well as an automatic type checking mode in Lash, a fork of Satallax, the leading tableaux-based prover for HOL. Our method is sound and complete with respect to provability in DHOL. Completeness is guaranteed by the incorporation of a sound and complete translation from DHOL to HOL recently proposed by Rothgang et al. While this translation can already be used as a preprocessing step to any HOL prover, to achieve better performance, our system directly works in DHOL. Moreover, experimental results show that the DHOL version of Lash can outperform all major HOL provers executed on the translation. |
| 22 | A Certified Proof Checker for Deep Neural Network Verification in Imandra | 2024-05-17 | 展开Recent advances in the verification of deep neural networks (DNNs) have opened the way for a broader usage of DNN verification technology in many application areas, including safety-critical ones. However, DNN verifiers are themselves complex programs that have been shown to be susceptible to errors and numerical imprecision; this, in turn, has raised the question of trust in DNN verifiers. One prominent attempt to address this issue is enhancing DNN verifiers with the capability of producing certificates of their results that are subject to independent algorithmic checking. While formulations of Marabou certificate checking already exist on top of the state-of-the-art DNN verifier Marabou, they are implemented in C++, and that code itself raises the question of trust (e.g., in the precision of floating point calculations or guarantees for implementation soundness). Here, we present an alternative implementation of the Marabou certificate checking in Imandra -- an industrial functional programming language and an interactive theorem prover (ITP) -- that allows us to obtain full proof of certificate correctness. The significance of the result is two-fold. Firstly, it gives stronger independent guarantees for Marabou proofs. Secondly, it opens the way for the wider adoption of DNN verifiers in interactive theorem proving in the same way as many ITPs already incorporate SMT solvers. |
| 23 | Magnushammer: A Transformer-Based Approach to Premise Selection | 2023-03-08 | 展开This paper presents a novel approach to premise selection, a crucial reasoning task in automated theorem proving. Traditionally, symbolic methods that rely on extensive domain knowledge and engineering effort are applied to this task. In contrast, this work demonstrates that contrastive training with the transformer architecture can achieve higher-quality retrieval of relevant premises, without the engineering overhead. Our method, Magnushammer, outperforms the most advanced and widely used automation tool in interactive theorem proving called Sledgehammer. On the PISA and miniF2F benchmarks Magnushammer achieves |
感谢原始项目 @zezhishao/DailyArXiv 提供的灵感。