TIGER Lab

All

46 repositories

verl-tool
Public
A version of verl to support tool use
agent learning reinforcement llm
Python
•
MIT License
•26•330•4•1•Updated Aug 15, 2025Aug 15, 2025
VLM2Vec
Public
This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR 2025]
benchmark representation-learning image-retrieval embedding vlm multimodal rag video-retrieval contrastive-learning mmeb
Python
•
Apache License 2.0
•29•368•10•0•Updated Aug 14, 2025Aug 14, 2025
Vamba
Public
Code for the paper "Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers" [ICCV 2025]
video vlm llm
Python
•
MIT License
•9•82•2•0•Updated Jul 28, 2025Jul 28, 2025
VideoEval-Pro
Public
More reliable Video Understanding Evaluation
video evaluation understanding multimodal
Python
•0•11•0•0•Updated Jul 28, 2025Jul 28, 2025
TheoremExplainAgent
Public
Official Repo for "TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding" [ACL 2025 oral]
rag manim manim-animations llm-agents manim-video
Python
•
MIT License
•171•1.4k•8•1•Updated Jul 27, 2025Jul 27, 2025
ABC
Public
ABC: Achieving Better Control of Multimodal Embeddings using VLMs [TMLR2025]
information-retrieval multimodal
Python
•
MIT License
•2•15•0•0•Updated Jul 24, 2025Jul 24, 2025
CritiqueFineTuning
Public
Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]
fine-tuning languagemodel
Python
•
MIT License
•10•169•1•0•Updated Jul 8, 2025Jul 8, 2025
ScholarCopilot
Public
ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations [COLM 2025]
lm copilot rag
Python
•
MIT License
•23•225•0•0•Updated Jul 8, 2025Jul 8, 2025
MEGA-Bench
Public
This repo contains the code for "MEGA-Bench Scaling Multimodal Evaluation to over 500 Real-World Tasks" [ICLR2025]
benchmark evaluation multimodal
Python
•
Apache License 2.0
•6•73•5•0•Updated Jul 1, 2025Jul 1, 2025
Pixel-Reasoner
Public
Pixel-Level Reasoning Model trained with RL
reasoning multimodal llm
Python
•
MIT License
•6•191•1•0•Updated Jun 30, 2025Jun 30, 2025
DisProtEdit
Public
Official Repo for "DisProtEdit: Exploring Disentangled Representations for Multi-Attribute Protein Editing" [ICMLW 2025]
protein protein-editing
Python
•
MIT License
•0•2•0•0•Updated Jun 20, 2025Jun 20, 2025
QuickVideo
Public
Quick Long Video Understanding
video multimodal-learning multimodal llm
Python
•
MIT License
•4•61•1•0•Updated Jun 14, 2025Jun 14, 2025
General-Reasoner
Public
General Reasoner: Advancing LLM Reasoning Across All Domains
rl reasoning llm
Python
•7•162•1•0•Updated Jun 10, 2025Jun 10, 2025
VisCoder
Public
The official code of "VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation"
Python
•
Apache License 2.0
•0•10•0•0•Updated Jun 7, 2025Jun 7, 2025
One-Shot-CFT
Public
The official repo for “Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem”
lm critique reasoning
Python
•
Apache License 2.0
•4•28•0•0•Updated Jun 6, 2025Jun 6, 2025
VL-Rethinker
Public
The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning"
reasoning vlm multimodal llm
Python
•
Apache License 2.0
•5•136•4•0•Updated Jun 5, 2025Jun 5, 2025
StructEval
Public
Evaluating LLMs' abilities to generate structural output.
benchmark structure evaluation
Python
•
Apache License 2.0
•1•7•0•0•Updated May 27, 2025May 27, 2025
QuickCodec
Public
A More Efficient Video Codec
video codec
Cython
•
BSD 3-Clause "New" or "Revised" License
•0•2•0•0•Updated May 23, 2025May 23, 2025
VisualWebInstruct
Public
The official repo for "VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search"
vlm llm
Python
•
MIT License
•1•26•0•0•Updated May 6, 2025May 6, 2025
ImagenHub
Public
A one-stop library to standardize the inference and evaluation of all the conditional image generation models. [ICLR 2024]
deep-learning pytorch image-editing generative-art image-generation diffusion-models stable-diffusion generative-ai
Python
•
MIT License
•18•171•2•1•Updated Apr 16, 2025Apr 16, 2025
AceCoder
Public
The official repo for "AceCoder: Acing Coder RL via Automated Test-Case Synthesis" [ACL25]
code llm codellm
Python
•
MIT License
•3•86•4•0•Updated Apr 9, 2025Apr 9, 2025
Mantis
Public
Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR 2024]
language video vision mantis vlm multimodal lmm fuyu mllm llava-llama3
Python
•
Apache License 2.0
•20•225•4•1•Updated Mar 23, 2025Mar 23, 2025
MMLU-Pro
Public
The code and data for "MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark" [NeurIPS 2024]
evaluation llm
Python
•
Apache License 2.0
•42•277•6•0•Updated Feb 28, 2025Feb 28, 2025
VISTA
Public
The code for "VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by VIdeo SpatioTemporal Augmentation" [CVPR2025]
lm vlm multimodal
Python
•0•19•0•0•Updated Feb 27, 2025Feb 27, 2025
LongICLBench
Public
Code and Data for "Long-context LLMs Struggle with Long In-context Learning" [TMLR2025]
large-language-models
Python
•
MIT License
•8•106•1•0•Updated Feb 20, 2025Feb 20, 2025
VideoScore
Public
official repo for "VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation" [EMNLP2024]
language machine-learning
Python
•
MIT License
•5•94•4•0•Updated Feb 14, 2025Feb 14, 2025
VideoGenHub
Public
A one-stop library to standardize the inference and evaluation of all the conditional video generation models.
deep-learning pytorch video-generation diffusion-models generative-ai
Python
•
MIT License
•7•49•1•1•Updated Feb 13, 2025Feb 13, 2025
PixelWorld
Public
The official code of "PixelWorld: Towards Perceiving Everything as Pixels"
vlm llm
Python
•1•14•1•0•Updated Feb 7, 2025Feb 7, 2025
KB-BINDER
Public
"Few-shot In-context Learning for Knowledge Base Question Answering" [ACL2023]
kb llm
Python
•
MIT License
•8•62•6•0•Updated Jan 27, 2025Jan 27, 2025
OmniEdit
Public
Official Repo for Paper "OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision" [ICLR2025]
imagegeneration diffusionmodel imageediting
MIT License
•3•125•4•0•Updated Jan 27, 2025Jan 27, 2025