Spatial Interaction Intelligence
ZGCA HMI LAB
The core of the next stage of embodied intelligence is not merely language or action, but interpretable, generative, and closed-loop spatial interaction among humans, machines, and environments.
CognitionUnderstand spatial and human-interaction knowledge
ImaginationPredict world and ego-state evolution
SkillGenerate spatially consistent embodied behavior

Research Directions
Interaction Priors
- 01Scene Parsing
- 02Scene Reconstruction
- 03Hand-Object Contact
Interaction Generation
- 01World State Rollout
- 02Manipulation Action Generation
- 03Navigation Action Generation
Research Updates
- 2026-02-20Rex-Omni Accepted by CVPR 2026
- 2026-01-26Rex-Thinker Accepted by ICLR 2026

