Repositories list

• OpenS2V-Nexus

  Public
  OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

  benchmarkdatasetevaluation-kit+ 7video-generationimage-to-videotext-to-videoaigctext-to-video-generationimage-to-video-generationsubject-to-video

  Jupyter Notebook

  •

  Apache License 2.0

  •4•151•4•0•Updated Aug 19, 2025Aug 19, 2025

• WISE

  Public
  WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation

  Python

  •3•143•1•0•Updated Aug 15, 2025Aug 15, 2025

• NeuralGS

  Public
  📌 [Arxiv2025] Official implementation of "NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representation"

  3•172•1•0•Updated Aug 14, 2025Aug 14, 2025

• UniWorld-V1

  Public
  UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

  image-editingdiffusionvlm+ 6image-understandingunifylow-level-visionhigh-level-featuretext-to-image-generationunify-ai

  Python

  •

  MIT License

  •21•688•3•0•Updated Aug 1, 2025Aug 1, 2025

• ImgEdit

  Public
  ImgEdit: A Unified Image Editing Dataset and Benchmark

  Python

  •0•163•1•0•Updated Jul 27, 2025Jul 27, 2025

• LLaVA-CoT

  Public
  [ICCV 2025] LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning

  Python

  •

  Apache License 2.0

  •81•2.1k•0•0•Updated Jul 22, 2025Jul 22, 2025

• MagicTime

  Public
  [TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

  time-lapsevideo-generationdiffusion-models+ 5text-to-videolong-video-generationtime-lapse-datasetopen-sora-planmetamorphic-video-generation

  Python

  •

  Apache License 2.0

  •125•1.3k•9•0•Updated Jul 21, 2025Jul 21, 2025

• Open-Sora-Plan

  Public
  This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

  Python

  •

  MIT License

  •1.1k•12k•247•14•Updated Jul 19, 2025Jul 19, 2025

• MoE-LLaVA

  Public
  【TMM 2025🔥】 Mixture-of-Experts for Large Vision-Language Models

  moemulti-modalmixture-of-experts+ 1large-vision-language-model

  Python

  •

  Apache License 2.0

  •139•2.2k•64•0•Updated Jul 15, 2025Jul 15, 2025

• AsFT

  Public
  Code for the paper "AsFT: Anchoring Safety During LLM Fune-Tuning Within Narrow Safety Basin".

  Python

  •

  Other

  •0•25•0•0•Updated Jul 10, 2025Jul 10, 2025

• Look-Back

  Public
  This repository is the official implementation of "Look-Back: Implicit Visual Re-focusing in MLLM Reasoning".

  Python

  •1•43•0•0•Updated Jul 10, 2025Jul 10, 2025

• HoloTime

  Public
  [ACM MM 2025] HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation

  video-generationvideo-datasetdiffusion-models+ 4panoramic-videos4d-reconstruction3d-gaussian-splatting4d-generation

  Python

  •

  MIT License

  •10•128•1•0•Updated Jul 5, 2025Jul 5, 2025

• ConsisID

  Public
  [CVPR 2025 Highlight🔥] Identity-Preserving Text-to-Video Generation by Frequency Decomposition

  video-generatordiffusionvideo-generation+ 5diffusion-modelstext-to-videovideogenerationvideo-generation-datasetidentity-preserving

  Python

  •

  Apache License 2.0

  •40•749•33•0•Updated Jun 8, 2025Jun 8, 2025

• GS2E

  Public
  [Arxiv 2025] Implementation of "GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation"

  eventcameras

  Apache License 2.0

  •0•14•0•0•Updated Jun 1, 2025Jun 1, 2025

• ProLLaMA

  Public
  A Protein Large Language Model for Multi-Task Protein Language Processing

  Python

  •

  Apache License 2.0

  •22•189•2•1•Updated May 27, 2025May 27, 2025

• ChronoMagic-Bench

  Public
  [NeurIPS 2024 D&B Spotlight🔥] ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation

  benchmarkevaluationdataset+ 10time-lapseevaluation-kitvideo-generationdiffusion-modelstext-to-videoaigctime-lapse-dataset+ 3

  Python

  •

  Apache License 2.0

  •15•207•0•0•Updated May 27, 2025May 27, 2025

• WF-VAE

  Public
  [CVPR 2025🔥] Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model

  Python

  •

  Apache License 2.0

  •7•166•2•0•Updated May 11, 2025May 11, 2025

• UniLLM

  Public
  Python

  •0•3•0•0•Updated Apr 2, 2025Apr 2, 2025

• DreamDance

  Public
  0•74•1•0•Updated Mar 18, 2025Mar 18, 2025

• EvaGaussians

  Public
  3•56•2•0•Updated Mar 16, 2025Mar 16, 2025

• SwapAnyone

  Public
  An official implementation of SwapAnyone.

  MIT License

  •5•65•4•0•Updated Mar 14, 2025Mar 14, 2025

• Reasoning-Attack

  Public
  7•134•3•0•Updated Feb 28, 2025Feb 28, 2025

• Cycle3D

  Public
  [AAAI 2025🔥] Official implementation of Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle

  Python

  •

  MIT License

  •7•209•3•0•Updated Feb 16, 2025Feb 16, 2025

• PiCO

  Public
  [ICLR'25] PiCO: Peer Review in LLMs based on the Consistency Optimization, https://arxiv.org/pdf/2402.01830

  Python

  •4•36•0•0•Updated Feb 16, 2025Feb 16, 2025

• GPT-as-Language-Tree

  Public
  GPT as a Monte Carlo Language Tree: A Probabilistic Perspective

  0•45•0•0•Updated Jan 18, 2025Jan 18, 2025

• ChatLaw

  Public
  ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型

  GNU Affero General Public License v3.0

  •583•7.3k•61•2•Updated Jan 4, 2025Jan 4, 2025

• Next-Patch-Prediction

  Public
  Python

  •3•133•0•0•Updated Jan 2, 2025Jan 2, 2025

• N-LoRA

  Public
  【COLING 2025🔥】Code for the paper "Is Parameter Collision Hindering Continual Learning in LLMs?".

  Python

  •

  Apache License 2.0

  •1•35•1•0•Updated Dec 5, 2024Dec 5, 2024

• Video-LLaVA

  Public
  【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

  multi-modalinstruction-tuninglarge-vision-language-model

  Python

  •

  Apache License 2.0

  •239•3.3k•119•6•Updated Dec 3, 2024Dec 3, 2024

• LLaVA-o1

  Public
  1•56•0•0•Updated Nov 21, 2024Nov 21, 2024