Skip to content
View xinggangw's full-sized avatar

Organizations

@hustvl

Block or report xinggangw

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
xinggangw/README.md

WSI Labs (World Superintelligence Labs)

I am building World Superintelligence Labs (WSI Labs) alongside a group of talented students. Together, we work toward embodied general superintelligence — AI systems that understand physical causality, reason across continuous time and space, and plan reliable actions in the real world.

Website: https://wsilabs.xyz


Research Focus

  • Physical world models — compact latent representations preserving causal and geometric structure
  • Map-free intelligent driving — scene understanding and local physics without brittle HD maps
  • Embodied robotics — perception, memory, and action for real environments
  • High-dimensional planning — reasoning under constraints with safety guardrails

Build world model with superintelligence step by step.

Pinned Loading

  1. hustvl/Vim hustvl/Vim Public

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

    Python 3.9k 289

  2. hustvl/4DGaussians hustvl/4DGaussians Public

    [CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

    Jupyter Notebook 3.8k 374

  3. hustvl/LightningDiT hustvl/LightningDiT Public

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

    Python 1.5k 57

  4. hustvl/DiffusionDrive hustvl/DiffusionDrive Public

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

    Python 1.4k 136

  5. hustvl/MoDA hustvl/MoDA Public

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

    Python 270 9

  6. hustvl/DiG hustvl/DiG Public

    [CVPR 2025] DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

    Python 182 11