Skip to content
@hustvl

HUST Vision Lab

HUST Vision Lab of the School of EIC in HUST. Lab Lead @xinggangw

Welcome to the Vision Lab @ HUST!

🙋‍♀️ Introduction

Hello! This is the GitHub space for the Vision Lab led by Professor Xinggang Wang. We are based at the Artificial Intelligence Institute, School of Electronic Information and Communications, Huazhong University of Science and Technology (HUST).

Our research focuses on computer vision and deep learning. We are particularly interested in:

  • Multimodal Foundation Models
  • Visual Representation Learning
  • Object Detection, Segmentation, and Tracking
  • End-to-end Autonomous Driving
  • Novel Neural Architectures

Our group strives to push the boundaries of visual intelligence and has produced highly influential works in the field, including CCNet, Mask Scoring R-CNN, FairMOT, ByteTrack, EVA, MapTR, Vectorized Autonomous Driving (VAD), DiffusionDrive, Vision Mamba (Vim), 4D Gaussian Splatting (4DGS), YOLOS, YOLO-World, and LightningDiT & VA-VAE.

🌈 Contribution Guidelines & Collaboration

We actively contribute to the research community through publications and open-source projects.

  • Research Collaboration: We are open to collaborations in our areas of interest. Please feel free to reach out to Prof. Xinggang Wang (xgwang # hust.edu.cn).
  • Prospective Students: Our group has a strong track record of mentoring Ph.D. and Master's students who lead impactful publications. Interested students can find more information on Prof. Wang's faculty page.
  • Using Our Code: You are welcome to explore and use the code in our repositories. Please ensure you cite the corresponding publications appropriately. Specific details can usually be found in the README files of individual repositories.
  • Contributing to Projects: For guidelines on contributing to specific projects (e.g., bug reports, pull requests), please check the individual repositories.

👩‍💻 Useful Resources

Pinned Loading

  1. VimVimPublic

    [ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

    Python 3.9k 288

  2. LightningDiTLightningDiTPublic

    [CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

    Python 1.5k 56

  3. VADVADPublic

    [ICCV 2023 & ICLR 2026] VAD: Vectorized Scene Representation for Efficient Autonomous Driving

    Python 1.4k 169

  4. MapTRMapTRPublic

    [ICLR'23 Spotlight & ECCV'24 & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction

    Python 1.5k 249

  5. DiffusionDriveDiffusionDrivePublic

    [CVPR 2025 Highlight] Truncated Diffusion Model for Real-Time End-to-End Autonomous Driving

    Python 1.5k 147

  6. MoDAMoDAPublic

    An hardware-aware Efficient Implementation for "Mixture-of-Depths Attention".

    Python 274 10

Repositories

Showing 10 of 127 repositories
  • Moebius Public

    [ECCV 2026] Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

    hustvl/Moebius's past year of commit activity
    Python 515Apache-2.0 44 2 1 Updated Aug 12, 2026
  • Senna Public

    [IJCV 2026] Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving

    hustvl/Senna's past year of commit activity
    Python 553Apache-2.0 49 29 0 Updated Aug 12, 2026
  • FasterWAM Public

    Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models

    hustvl/FasterWAM's past year of commit activity
    Python 31Apache-2.0 2 0 0 Updated Aug 8, 2026
  • DreamWAM Public
    hustvl/DreamWAM's past year of commit activity
    Python 33 0 0 0 Updated Aug 6, 2026
  • EOVSAM Public
    hustvl/EOVSAM's past year of commit activity
    Python 10 0 0 0 Updated Aug 4, 2026
  • ControlAR Public

    [ICLR 2025] ControlAR: Controllable Image Generation with Autoregressive Models

    hustvl/ControlAR's past year of commit activity
    Python 329Apache-2.0 10 12 0 Updated Aug 2, 2026
  • OmniMamba Public

    [ECCV 2026] OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models

    hustvl/OmniMamba's past year of commit activity
    Python 126MIT 5 4 0 Updated Jul 27, 2026
  • WeakTr Public

    [TIP, IEEE Transactions on Image Processing] WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation

    hustvl/WeakTr's past year of commit activity
    Python 140MIT 3 10 0 Updated Jul 17, 2026
  • Turbo-VAED Public

    [AAAI 2026] Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices

    hustvl/Turbo-VAED's past year of commit activity
    Python 139 2 15 0 Updated Jul 10, 2026
  • DiffusionVL Public

    [ECCV 2026] DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models

    hustvl/DiffusionVL's past year of commit activity
    Python 160Apache-2.0 12 1 0 Updated Jul 8, 2026

Top languages

Loading…

Most used topics

Loading…