Skip to content

@OpenGVLab OpenGVLab

All

    Repositories list

    95 repositories

    • RSI-Nav

      Public
      vlmembodied-agentmllm
      vlmembodied-agentmllmvision-language-modelvision-language-navigationrecursive-self-improvement
      Python
      •
      MIT License
      •0•34•2•0•Updated Oct 14, 2026Oct 14, 2026

    • GenExam

      Public
      [ICML 2026] GenExam: A Multidisciplinary Text-to-Image Exam
      benchmarkimage-generationtext-to-image-generation
      benchmarkimage-generationtext-to-image-generation
      Python
      •
      MIT License
      •4•73•0•0•Updated Sep 26, 2026Sep 26, 2026

    • Future-L1

      Public
      [EMNLP 2026 Main] Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction
      reinforcement-learningcomputer-visionvideo-understanding
      reinforcement-learningcomputer-visionvideo-understandingvideo-eventsfuture-predictionvideo-reasoningrlhfvision-language-modelmultimodal-llmlatent-reasoning
      Python
      •1•39•0•0•Updated Sep 18, 2026Sep 18, 2026

    • SID-VLN

      Public
      [ECCV 2026] Learning Goal-Oriented Language-Guided Navigation with Self-Improving Demonstrations at Scale
      Python
      •
      MIT License
      •3•15•0•0•Updated Jul 21, 2026Jul 21, 2026

    • VideoChat-Flash

      Public
      [ICLR2026] VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
      Python
      •
      MIT License
      •21•531•11•0•Updated Jul 19, 2026Jul 19, 2026

    • Ask-Anything

      Public
      [CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
      chatvideogradio
      chatvideogradiobig-modelvideo-understandingcaptioning-videosvideo-question-answeringfoundation-modelslarge-modellarge-language-models
      Python
      •
      MIT License
      •269•3.4k•70•5•Updated Jul 17, 2026Jul 17, 2026

    • InternVideo

      Public
      [ECCV2024] Video Foundation Models & Data for Multimodal Understanding
      benchmarkaction-recognitionvideo-understanding
      benchmarkaction-recognitionvideo-understandingvideo-dataself-supervisedmultimodalvideo-datasetopen-set-recognitionvideo-retrievalvideo-question-answering
      Python
      •
      Apache License 2.0
      •163•2.4k•143•4•Updated Jul 2, 2026Jul 2, 2026

    • STM-Evaluation

      Public
      Python
      •
      MIT License
      •6•70•1•0•Updated Jun 9, 2026Jun 9, 2026

    • VRBench

      Public
      [ICCV 2025] A Benchmark for Multi-Step Reasoning in Long Narrative Videos
      benchmarkdatasetvideo-understanding
      benchmarkdatasetvideo-understandingvlmevaluation-kitmulti-step-reasoningvideo-reasoningllm
      Python
      •
      Apache License 2.0
      •0•28•2•0•Updated Jun 4, 2026Jun 4, 2026

    • RIVER

      Public
      [ICLR 2026] RIVER: A Real-Time Interaction Benchmark for Video LLMs
      real-timestreaming-videovideo-understanding
      real-timestreaming-videovideo-understandingmemory-benchmarkvideo-benchmarklong-video-understandingmultimodal-llmvideo-llmmultimodal-benchmarkonline-video-und
      Python
      •0•19•0•0•Updated Apr 20, 2026Apr 20, 2026

    • EfficientQAT

      Public
      [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models
      Python
      •
      MIT License
      •38•354•13•0•Updated Apr 10, 2026Apr 10, 2026

    • MMT-Bench

      Public
      [ICML 2024] | MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
      Python
      •4•119•1•0•Updated Apr 6, 2026Apr 6, 2026

    • V2PE

      Public
      [ICCV2025] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding
      Python
      •
      MIT License
      •2•61•2•0•Updated Apr 4, 2026Apr 4, 2026

    • InternVL-U

      Public
      InternVL-U is a 4B-parameter unified multimodal model (UMM) that brings multimodal understanding, reasoning, image generation, image editing into a single frame…
      Python
      •
      MIT License
      •17•299•9•1•Updated Mar 21, 2026Mar 21, 2026

    • Vlaser

      Public
      Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning
      Python
      •
      MIT License
      •1•49•3•0•Updated Mar 18, 2026Mar 18, 2026

    • GenEditEvalKit

      Public
      The first unified, efficient, and extensible evaluation toolkit for evaluating image generation and editing models across multiple benchmarks.
      Jupyter Notebook
      •
      MIT License
      •4•0•0•0•Updated Mar 7, 2026Mar 7, 2026

    • VKnowU

      Public
      VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs
      reinforcement-learningvideo-understandingcommonsense-reasoning
      reinforcement-learningvideo-understandingcommonsense-reasoningvisual-reasoningintuitive-physicsvideo-question-answeringvideo-benchmarkhuman-centricmllmmultimodal-llm
      Python
      •1•21•0•0•Updated Feb 3, 2026Feb 3, 2026

    • MetaCaptioner

      Public
      Python
      •4•54•2•0•Updated Jan 27, 2026Jan 27, 2026

    • ScaleCUA

      Public
      [ICLR 2026 Oral] ScaleCUA is the open-sourced computer use agents that can operate on cross-platform environments (Windows, macOS, Ubuntu, Android).
      datamodelsgui-agents
      datamodelsgui-agentscomputer-use-agentsscalecuaonline-evaluation-suite
      Python
      •
      Apache License 2.0
      •82•1.1k•15•2•Updated Jan 7, 2026Jan 7, 2026

    • GUI-Odyssey

      Public
      [ICCV 2025] GUIOdyssey is a comprehensive dataset for training and evaluating cross-app navigation agents. GUIOdyssey consists of 8,834 episodes from 6 mobile d…
      Python
      •10•162•10•0•Updated Jan 3, 2026Jan 3, 2026

    • SDLM

      Public
      [Accepted By EMNLP 2026 Main Conference] Sequential Diffusion Language Model (SDLM) enhances pre-trained autoregressive language models by adaptively determinin…
      gptlanguage-modeldiffusion-models
      gptlanguage-modeldiffusion-modelsllm
      Python
      •
      MIT License
      •4•99•0•0•Updated Dec 27, 2025Dec 27, 2025

    • vinci

      Public
      Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model
      Python
      •4•95•2•0•Updated Nov 27, 2025Nov 27, 2025

    • OmniQuant

      Public
      [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
      quantizationlarge-language-modelsllm
      quantizationlarge-language-modelsllm
      Python
      •
      MIT License
      •93•964•31•2•Updated Nov 26, 2025Nov 26, 2025

    • ExpVid

      Public
      0•13•0•0•Updated Oct 28, 2025Oct 28, 2025

    • VideoChat-R1

      Public
      [NIPS2025] VideoChat-R1 & R1.5: Enhancing Spatio-Temporal Perception and Reasoning via Reinforcement Fine-Tuning
      Python
      •10•269•23•0•Updated Oct 18, 2025Oct 18, 2025

    • NaViL

      Public
      Python
      •
      MIT License
      •7•95•0•0•Updated Oct 10, 2025Oct 10, 2025

    • PonderV2

      Public
      [T-PAMI 2025] PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
      3d-visionpretrainingfoundation-models
      3d-visionpretrainingfoundation-models
      Python
      •
      MIT License
      •8•378•0•0•Updated Sep 30, 2025Sep 30, 2025

    • InternVL

      Public
      [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
      image-classificationgptmulti-modalsemantic-segmentationvideo-classificationimage-text-retrievalllmvision-language-modelgpt-4vvit-6b
      Python
      •
      MIT License
      •792•10k•304•12•Updated Sep 22, 2025Sep 22, 2025

    • EgoExoLearn

      Public
      [CVPR 2024] Data and benchmark code for the EgoExoLearn dataset
      Python
      •
      MIT License
      •2•92•3•0•Updated Aug 26, 2025Aug 26, 2025

    • PIIP

      Public
      [NeurIPS 2024 Spotlight ⭐️ & TPAMI 2025] Parameter-Inverted Image Pyramid Networks (PIIP)
      computer-visionimage-classificationobject-detection
      computer-visionimage-classificationobject-detectionsemantic-segmentationinstance-segmentationvision-transformermultimodal-large-language-modelsvision-language-models
      Python
      •
      MIT License
      •5•113•2•0•Updated Aug 5, 2025Aug 5, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.