Repositories list

• VP-VLA

  Public
  VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models

  Python

  •

  Other

  •00 forks•66 stars•00 issues•00 pull requests•Updated Apr 12, 2026Apr 12, 2026

• DreamOmni2

  Public
  This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation (CVPR2026 Highlight)''

  image-editingimage-generationunified-generation-editing-model

  image-editingimage-generationunified-generation-editing-model

  Python

  •

  Apache License 2.0

  •180180 forks•2.1k2.1k stars•2323 issues•11 pull request•Updated Apr 11, 2026Apr 11, 2026

• Block-Approximate-Sparse-Attention

  Public

  JIA-Lab-research/Block-Approximate-Sparse-Attention’s past year of commit activity
  [CVPR26] Official implementation of CVPR2026 Findings Paper 'Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention…

  00 forks•66 stars•00 issues•00 pull requests•Updated Apr 7, 2026Apr 7, 2026

• MGM-Omni

  Public
  MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech

  text-to-speechmultimodalmulti-modality+ 2

  text-to-speechmultimodalmulti-modalitymulti-modal-large-language-modelaudio-language-model

  Python

  •

  Apache License 2.0

  •1313 forks•214214 stars•44 issues•00 pull requests•Updated Mar 26, 2026Mar 26, 2026

• RePlan

  Public
  RePlan: Reasoning-Guided Region Planning for Complex Instruction-Based Image Editing

  benchmarkcontrolimage-editing+ 4

  benchmarkcontrolimage-editingplanningeditinginpaintinggrpo

  Python

  •

  Apache License 2.0

  •33 forks•6363 stars•11 issue•00 pull requests•Updated Mar 19, 2026Mar 19, 2026

• VisionDirector

  Public
  CVPR 2026

  Python

  •00 forks•33 stars•00 issues•00 pull requests•Updated Mar 18, 2026Mar 18, 2026

• VisionReasoner

  Public
  VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning

  reinforcement-learningsegmentationobject-detection+ 5

  reinforcement-learningsegmentationobject-detectionmultimodalcounting-objectsvisual-perceptionmultimodal-large-language-modelsreasoning-language-models

  Python

  •

  Apache License 2.0

  •1515 forks•335335 stars•00 issues•00 pull requests•Updated Feb 9, 2026Feb 9, 2026

• Scaf-GRPO

  Public
  Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning

  Python

  •11 fork•1616 stars•00 issues•00 pull requests•Updated Feb 8, 2026Feb 8, 2026

• UnityVideo

  Public

  JIA-Lab-research/UnityVideo’s past year of commit activity
  [CVPR 2026]UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation

  MIT License

  •88 forks•214214 stars•33 issues•00 pull requests•Updated Jan 29, 2026Jan 29, 2026

• SearchGym

  Public
  Python

  •00 forks•99 stars•00 issues•00 pull requests•Updated Jan 23, 2026Jan 23, 2026

• TraveLLaMA

  Public
  Offical Repo for TraveLLaMA: A Multimodal Travel Assistant with Large-Scale Dataset and Structured Reasoning (AAAI 2026 Oral)

  00 forks•66 stars•11 issue•00 pull requests•Updated Jan 21, 2026Jan 21, 2026

• Seg-Zero

  Public
  Project Page For "Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement"

  reinforcement-learningsegmentationmultimodal+ 2

  reinforcement-learningsegmentationmultimodalmultimodel-large-language-modelreasoning-language-models

  Python

  •

  Apache License 2.0

  •3030 forks•624624 stars•44 issues•00 pull requests•Updated Jan 17, 2026Jan 17, 2026

• DreamOmni3

  Public
  This project is the official implementation of 'DreamOmni3: Scribble-based Editing and Generation''

  00 forks•3939 stars•22 issues•00 pull requests•Updated Dec 30, 2025Dec 30, 2025

• SmartSwitch

  Public
  SmartSwitch: Advancing LLM Reasoning by Overcoming Underthinking via Promoting Deeper Thought Exploration

  Python

  •00 forks•66 stars•00 issues•00 pull requests•Updated Oct 23, 2025Oct 23, 2025

• VisionThink

  Public
  [NeurIPS 2025] Efficient Reasoning Vision Language Models

  Python

  •

  Apache License 2.0

  •3030 forks•457457 stars•1414 issues•00 pull requests•Updated Sep 18, 2025Sep 18, 2025

• LSDBench

  Public
  A benchmark that focuses on the sampling dilemma in long-video tasks. Through well-designed tasks, it evaluates the sampling efficiency of long-video VLMs. (ICC…

  benchmarkvideo-understandingsampling-strategies+ 5

  benchmarkvideo-understandingsampling-strategiesreasoning-agentvision-language-modellong-video-understandingmultimodal-large-language-modelsvideo-understanding-dataset

  Python

  •

  Apache License 2.0

  •00 forks•2828 stars•00 issues•00 pull requests•Updated Aug 7, 2025Aug 7, 2025

• Jenga

  Public
  [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving

  Python

  •1414 forks•279279 stars•99 issues•00 pull requests•Updated Aug 4, 2025Aug 4, 2025

• VisionZip

  Public
  Official repository for VisionZip (CVPR 2025)

  efficiencymulti-modalityvision-language-model+ 1

  efficiencymulti-modalityvision-language-modelvlms

  Python

  •

  Apache License 2.0

  •2323 forks•425425 stars•2424 issues•00 pull requests•Updated Jul 21, 2025Jul 21, 2025

• Parametric-Contrastive-Learning

  Public
  Parametric Contrastive Learning (ICCV2021) & GPaCo (TPAMI 2023)

  pytorchsupervised-learningimagenet+ 10

  pytorchsupervised-learningimagenetimage-classificationclass-imbalanceimbalanced-dataimbalanced-learningtpamicontrastive-learningsupervised-contrastive-learning+ 3

  Python

  •

  MIT License

  •3232 forks•258258 stars•77 issues•00 pull requests•Updated Jul 21, 2025Jul 21, 2025

• TGDPO

  Public
  [ICML 2025] TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization

  alignmentpreference-learninglarge-language-models+ 5

  alignmentpreference-learninglarge-language-modelsllmrlhfpreference-alignmentdirect-preference-optimizationpreference-optimization

  Python

  •00 forks•1010 stars•00 issues•00 pull requests•Updated Jul 15, 2025Jul 15, 2025

• Video-P2P

  Public
  Video-P2P: Video Editing with Cross-attention Control

  image-editinggenerative-modelvideo-editing+ 2

  image-editinggenerative-modelvideo-editingtext-driven-editingstable-diffusion

  Python

  •2727 forks•431431 stars•55 issues•00 pull requests•Updated Jun 30, 2025Jun 30, 2025

• RL-GPT

  Public
  Python

  •22 forks•1010 stars•11 issue•00 pull requests•Updated Jun 30, 2025Jun 30, 2025

• MagicMirror

  Public
  [ICCV 2025] MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers

  44 forks•130130 stars•77 issues•00 pull requests•Updated Jun 26, 2025Jun 26, 2025

• Logits-Based-Finetuning

  Public
  Official Code of Logits-Based-Finetuning

  Python

  •99 forks•9090 stars•00 issues•00 pull requests•Updated Jun 14, 2025Jun 14, 2025

• LLMGA

  Public
  This project is the official implementation of 'LLMGA: Multimodal Large Language Model based Generation Assistant', ECCV2024 Oral

  image-editingimage-generationmulti-modal+ 5

  image-editingimage-generationmulti-modalaigcllmlarge-language-modelmllmimage-design-assistant

  Python

  •

  Apache License 2.0

  •2525 forks•398398 stars•33 issues•00 pull requests•Updated Jun 2, 2025Jun 2, 2025

• ARPO

  Public
  Official Implementation of ARPO: End-to-End Policy Optimization for GUI Agents with Experience Replay

  Python

  •

  Apache License 2.0

  •1111 forks•158158 stars•99 issues•00 pull requests•Updated May 29, 2025May 29, 2025

• MoTCoder

  Public
  This is the official code repository of MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks.

  natural-language-processingprogrammingcode+ 3

  natural-language-processingprogrammingcodeappscode-generationlarge-language-models

  Python

  •33 forks•8585 stars•77 issues•00 pull requests•Updated Mar 30, 2025Mar 30, 2025

• Open-Code-Zero

  Public
  00 forks•11 star•00 issues•00 pull requests•Updated Mar 10, 2025Mar 10, 2025

• LISA

  Public
  Project Page for "LISA: Reasoning Segmentation via Large Language Model"

  segmentationmulti-modalllm+ 1

  segmentationmulti-modalllmlarge-language-model

  Python

  •

  Apache License 2.0

  •206206 forks•2.6k2.6k stars•114114 issues•00 pull requests•Updated Feb 16, 2025Feb 16, 2025

• Step-DPO

  Public
  Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

  mathreasoningdpo+ 1

  mathreasoningdpollm

  Python

  •1616 forks•395395 stars•1818 issues•00 pull requests•Updated Jan 19, 2025Jan 19, 2025