Skip to content

@hustvl HUST Vision Lab

All

    Repositories list

    132 repositories

    • Multimodal-Flow

      Public
      A Fully Continuous Multimodal Flow Framework For Flexible Multimodal Sequence Modeling.
      Python
      •
      Apache License 2.0
      •1•37•2•0•Updated Oct 8, 2026Oct 8, 2026

    • ReWAM

      Public
      1•19•0•0•Updated Sep 29, 2026Sep 29, 2026

    • Bridge3D

      Public
      HTML
      •0•13•0•0•Updated Sep 27, 2026Sep 27, 2026

    • InfiniteVL

      Public
      [NeurIPS 2026] InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models
      Python
      •
      Apache License 2.0
      •5•120•5•0•Updated Sep 24, 2026Sep 24, 2026

    • .github

      Public
      0•0•0•0•Updated Sep 20, 2026Sep 20, 2026

    • MotionVLA

      Public
      [CoRL2026] MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model
      Python
      •
      Apache License 2.0
      •0•19•0•0•Updated Sep 7, 2026Sep 7, 2026

    • FasterWAM

      Public
      Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models
      robot-manipulationworld-action-model
      robot-manipulationworld-action-model
      Python
      •
      Apache License 2.0
      •8•76•0•0•Updated Aug 31, 2026Aug 31, 2026

    • DreamWAM

      Public
      Python
      •
      Apache License 2.0
      •1•45•0•0•Updated Aug 28, 2026Aug 28, 2026

    • EOVSAM

      Public
      Python
      •0•17•1•0•Updated Aug 25, 2026Aug 25, 2026

    • ChangeDETR

      Public
      Python
      •0•3•0•0•Updated Aug 23, 2026Aug 23, 2026

    • Moebius

      Public
      [ECCV 2026] Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance
      Python
      •
      Apache License 2.0
      •45•545•3•1•Updated Aug 12, 2026Aug 12, 2026

    • Senna

      Public
      [IJCV 2026] Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving
      end-to-endautonomous-drivingvision-language-action-model
      end-to-endautonomous-drivingvision-language-action-model
      Python
      •
      Apache License 2.0
      •50•558•32•0•Updated Aug 12, 2026Aug 12, 2026

    • ControlAR

      Public
      [ICLR 2025] ControlAR: Controllable Image Generation with Autoregressive Models
      Python
      •
      Apache License 2.0
      •12•328•12•0•Updated Aug 2, 2026Aug 2, 2026

    • OmniMamba

      Public
      [ECCV 2026] OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models
      Python
      •
      MIT License
      •5•127•4•0•Updated Jul 27, 2026Jul 27, 2026

    • WeakTr

      Public
      [TIP, IEEE Transactions on Image Processing] WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation
      Python
      •
      MIT License
      •3•144•10•0•Updated Jul 17, 2026Jul 17, 2026

    • Turbo-VAED

      Public
      [AAAI 2026] Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices
      Python
      •2•143•16•0•Updated Jul 10, 2026Jul 10, 2026

    • DiffusionVL

      Public
      [ECCV 2026] DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models
      Python
      •
      Apache License 2.0
      •12•163•1•0•Updated Jul 8, 2026Jul 8, 2026

    • PixelHacker

      Public
      PixelHacker: Image Inpainting with Structural and Semantic Consistency
      Python
      •
      Apache License 2.0
      •54•524•14•1•Updated Jun 20, 2026Jun 20, 2026

    • EVA-X

      Public
      [Nature Portfolio, npj DigitalMed] EVA-X: A foundation model for general chest X-ray analysis with self-supervised learning
      Python
      •
      Apache License 2.0
      •15•105•6•0•Updated Jun 12, 2026Jun 12, 2026

    • Food-R1

      Public
      Python
      •
      Apache License 2.0
      •0•12•0•0•Updated Jun 4, 2026Jun 4, 2026

    • TransLight

      Public
      project page template
      JavaScript
      •2k•1•0•0•Updated May 26, 2026May 26, 2026

    • MobileI2V

      Public
      [ArXiv 2025] MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devices
      video-generationimage-to-videodiffusion-models
      video-generationimage-to-videodiffusion-modelsvideo-diffusion-transformers
      Python
      •
      Apache License 2.0
      •8•101•2•0•Updated May 20, 2026May 20, 2026

    • MoDA

      Public
      An hardware-aware Efficient Implementation for "Mixture-of-Depths Attention".
      Python
      •
      MIT License
      •9•280•3•0•Updated May 6, 2026May 6, 2026

    • RAD

      Public
      [NeurIPS 2025] RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning
      Python
      •
      MIT License
      •12•278•7•0•Updated Apr 17, 2026Apr 17, 2026

    • VGT

      Public
      Visual Generation Tuning
      Python
      •
      MIT License
      •1•102•1•0•Updated Apr 16, 2026Apr 16, 2026

    • 4DLangVGGT

      Public
      Official implementation of “4D LangVGGT: 4D Language-Visual Geometry Grounded Transformer”
      Python
      •
      MIT License
      •2•93•3•0•Updated Mar 25, 2026Mar 25, 2026

    • Spa3R

      Public
      Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning
      Python
      •
      MIT License
      •1•54•0•0•Updated Mar 25, 2026Mar 25, 2026

    • VAD

      Public
      [ICCV 2023 & ICLR 2026] VAD: Vectorized Scene Representation for Efficient Autonomous Driving
      end-to-endautonomous-driving
      end-to-endautonomous-driving
      Python
      •
      Apache License 2.0
      •171•1.4k•77•1•Updated Jan 31, 2026Jan 31, 2026

    • GaussTR

      Public
      [CVPR 2025] GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding
      Python
      •
      MIT License
      •13•220•1•0•Updated Jan 5, 2026Jan 5, 2026

    • DiffusionDriveV2

      Public
      DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving
      Python
      •
      MIT License
      •37•379•18•2•Updated Dec 29, 2025Dec 29, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.