ZGCA
HMI LAB
The team's research goal is to explore the next stage of embodied intelligence, moving from language and action capabilities toward analyzable, predictable, and closed-loop embodied interaction among humans, machines, and environments; the team is committed to building embodied interaction intelligence that can enter human activities, understand human intentions, and act naturally together with people.
CognitionUnderstand spatial and social interaction knowledge
ImaginationPredict world and ego-state evolution
SkillGenerate interaction-consistent embodied behavior

Research Directions
Near-field Interaction
- 01Scene Interaction Parsing
- 02Hand-Object Interaction Prediction
- 03Manipulation Model
Spatial Interaction
- 01Spatiotemporal State Representation
- 02Controllable World Model
- 03Navigation Model
Social Interaction
- 01Human-Robot Collaboration Framework
- 02Human-Robot Social Interaction Framework
- 03Multi-Embodied Agents
Research Overview
Research Updates
- 2026-07-10Two Papers Accepted by ACM MM 2026
- 2026-02-20Rex-Omni Accepted by CVPR 2026
- 2026-01-26Rex-Thinker Accepted by ICLR 2026

