Tsinghua Spatial Intelligence Lab (THUSI Lab)

Pinned Loading

1. Hstar Hstar Public

   [CVPR 2026] Thinking in 360°: Humanoid Visual Search in the Wild

   Python 150 3

2. GameVerse GameVerse Public

   [ICML 2026] GameVerse: Can Vision-Language Models Learn from Video-based Reflection?

   Python 55

3. PrismWAM PrismWAM Public

   Official implementation of PrismWAM: Decoupling State Representations in World Action Models

   Python 54 1

4. GameScaling GameScaling Public

   Scaling in Games: Continued Pre-Training for Embodied Agents in Diverse Virtual Worlds. Weights on Hugging Face.

   Python 441 23

5. RoboDoctor RoboDoctor Public

   The official code implementation for RoboDoctor: Training-Free Recursive Self-Improvement for Robot Policies

   Python 15

6. VSI-Super-Wild VSI-Super-Wild Public

   [ECCV 2026] Towards Spatial Supersensing in the Wild

   Python 22