Repositories list

• ScaleCUA

  Public
  ScaleCUA is the open-sourced computer use agents that can operate on cross-platform environments (Windows, macOS, Ubuntu, Android).

  datamodelsgui-agents+ 3computer-use-agentsscalecuaonline-evaluation-suite

  Python

  •

  Apache License 2.0

  •70•1.1k•13•0•Updated Jan 7, 2026Jan 7, 2026

• GUI-Odyssey

  Public

  OpenGVLab/GUI-Odyssey’s past year of commit activity
  [ICCV 2025] GUIOdyssey is a comprehensive dataset for training and evaluating cross-app navigation agents. GUIOdyssey consists of 8,834 episodes from 6 mobile devices, spanning 6 types of cross-app tasks, 212 apps, and 1.4K app combos.

  Python

  •8•143•11•0•Updated Jan 3, 2026Jan 3, 2026

• SDLM

  Public

  OpenGVLab/SDLM’s past year of commit activity
  Sequential Diffusion Language Model (SDLM) enhances pre-trained autoregressive language models by adaptively determining generation length and maintaining KV-cache compatibility, achieving high efficiency and throughput.

  gptlanguage-modeldiffusion-models+ 1llm

  Python

  •

  MIT License

  •3•87•0•0•Updated Dec 27, 2025Dec 27, 2025

• GenExam

  Public

  OpenGVLab/GenExam’s past year of commit activity
  GenExam: A Multidisciplinary Text-to-Image Exam

  benchmarkimage-generationtext-to-image-generation

  Python

  •

  MIT License

  •3•53•0•0•Updated Dec 18, 2025Dec 18, 2025

• VKnowU

  Public

  OpenGVLab/VKnowU’s past year of commit activity
  Python

  •1•11•0•0•Updated Dec 18, 2025Dec 18, 2025

• Vlaser

  Public

  OpenGVLab/Vlaser’s past year of commit activity
  Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

  Python

  •

  MIT License

  •0•39•0•0•Updated Dec 17, 2025Dec 17, 2025

• InternVideo

  Public

  OpenGVLab/InternVideo’s past year of commit activity
  [ECCV2024] Video Foundation Models & Data for Multimodal Understanding

  benchmarkaction-recognitionvideo-understanding+ 17video-dataself-supervisedmultimodalvideo-datasetopen-set-recognitionvideo-retrievalvideo-question-answering+ 10

  Python

  •

  Apache License 2.0

  •136•2.2k•133•3•Updated Dec 15, 2025Dec 15, 2025

• SID-VLN

  Public

  OpenGVLab/SID-VLN’s past year of commit activity
  Official implementation of: Learning Goal-Oriented Language-Guided Navigation with Self-Improving Demonstrations at Scale

  Python

  •

  MIT License

  •2•11•0•0•Updated Nov 29, 2025Nov 29, 2025

• vinci

  Public

  OpenGVLab/vinci’s past year of commit activity
  Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model

  Python

  •2•80•2•0•Updated Nov 27, 2025Nov 27, 2025

• OmniQuant

  Public

  OpenGVLab/OmniQuant’s past year of commit activity
  [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

  quantizationlarge-language-modelsllm

  Python

  •

  MIT License

  •72•885•27•1•Updated Nov 26, 2025Nov 26, 2025

• EfficientQAT

  Public

  OpenGVLab/EfficientQAT’s past year of commit activity
  [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

  Python

  •25•324•12•0•Updated Nov 26, 2025Nov 26, 2025

• VideoChat-Flash

  Public

  OpenGVLab/VideoChat-Flash’s past year of commit activity
  VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

  Python

  •

  MIT License

  •15•493•11•0•Updated Nov 18, 2025Nov 18, 2025

• MetaCaptioner

  Public
  Python

  •3•42•1•0•Updated Oct 31, 2025Oct 31, 2025

• ExpVid

  Public

  OpenGVLab/ExpVid’s past year of commit activity
  0•7•0•0•Updated Oct 28, 2025Oct 28, 2025

• VideoChat-R1

  Public

  OpenGVLab/VideoChat-R1’s past year of commit activity
  [NIPS2025] VideoChat-R1 & R1.5: Enhancing Spatio-Temporal Perception and Reasoning via Reinforcement Fine-Tuning

  Python

  •9•252•24•0•Updated Oct 18, 2025Oct 18, 2025

• NaViL

  Public
  Python

  •

  MIT License

  •7•88•0•0•Updated Oct 10, 2025Oct 10, 2025

• PonderV2

  Public

  OpenGVLab/PonderV2’s past year of commit activity
  [T-PAMI 2025] PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm

  3d-visionpretrainingfoundation-models

  Python

  •

  MIT License

  •8•369•0•0•Updated Sep 30, 2025Sep 30, 2025

• InternVL

  Public

  OpenGVLab/InternVL’s past year of commit activity
  [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

  image-classificationgptmulti-modal+ 9semantic-segmentationvideo-classificationimage-text-retrievalllmvision-language-modelgpt-4vvit-6b+ 2

  Python

  •

  MIT License

  •754•9.7k•289•6•Updated Sep 22, 2025Sep 22, 2025

• EgoExoLearn

  Public

  OpenGVLab/EgoExoLearn’s past year of commit activity
  [CVPR 2024] Data and benchmark code for the EgoExoLearn dataset

  Python

  •

  MIT License

  •2•77•3•0•Updated Aug 26, 2025Aug 26, 2025

• VRBench

  Public
  [ICCV 2025] A Benchmark for Multi-Step Reasoning in Long Narrative Videos

  benchmarkdatasetvideo-understanding+ 5vlmevaluation-kitmulti-step-reasoningvideo-reasoningllm

  Python

  •

  Apache License 2.0

  •0•23•1•0•Updated Aug 8, 2025Aug 8, 2025

• PIIP

  Public
  [NeurIPS 2024 Spotlight ⭐️ & TPAMI 2025] Parameter-Inverted Image Pyramid Networks (PIIP)

  computer-visionimage-classificationobject-detection+ 5semantic-segmentationinstance-segmentationvision-transformermultimodal-large-language-modelsvision-language-models

  Python

  •

  MIT License

  •5•107•2•0•Updated Aug 5, 2025Aug 5, 2025

• LORIS

  Public

  OpenGVLab/LORIS’s past year of commit activity
  [ICML2023] Long-Term Rhythmic Video Soundtracker

  music-generationpytorch-implementationmulti-modality+ 2diffusion-modelsaigc

  Python

  •

  MIT License

  •1•61•1•0•Updated Jul 28, 2025Jul 28, 2025

• TPO

  Public

  OpenGVLab/TPO’s past year of commit activity
  Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment

  Jupyter Notebook

  •6•64•1•0•Updated Jul 22, 2025Jul 22, 2025

• Docopilot

  Public

  OpenGVLab/Docopilot’s past year of commit activity
  [CVPR 2025] Docopilot: Improving Multimodal Models for Document-Level Understanding

  Python

  •

  MIT License

  •1•36•2•0•Updated Jul 22, 2025Jul 22, 2025

• Mono-InternVL

  Public

  OpenGVLab/Mono-InternVL’s past year of commit activity
  [CVPR 2025] Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training

  Python

  •

  MIT License

  •0•98•7•0•Updated Jul 18, 2025Jul 18, 2025

• ZeroGUI

  Public

  OpenGVLab/ZeroGUI’s past year of commit activity
  ZeroGUI: Automating Online GUI Learning at Zero Human Cost

  Python

  •

  Apache License 2.0

  •6•104•0•0•Updated Jul 17, 2025Jul 17, 2025

• MUTR

  Public

  OpenGVLab/MUTR’s past year of commit activity
  「AAAI 2024」 Referred by Multi-Modality: A Unified Temporal Transformers for Video Object Segmentation

  Python

  •

  MIT License

  •7•82•3•0•Updated Jun 13, 2025Jun 13, 2025

• PVC

  Public

  OpenGVLab/PVC’s past year of commit activity
  [CVPR 2025] PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models

  Python

  •

  MIT License

  •2•51•4•0•Updated Jun 12, 2025Jun 12, 2025

• FluxViT

  Public

  OpenGVLab/FluxViT’s past year of commit activity
  Make Your Training Flexible: Towards Deployment-Efficient Video Models

  Python

  •

  MIT License

  •0•35•1•0•Updated Jun 11, 2025Jun 11, 2025

• VeBrain

  Public
  Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces

  MIT License

  •7•87•4•0•Updated Jun 6, 2025Jun 6, 2025