MAKE
MACHINES
MORE
HUMAN.
I research 3D intelligence that sees, understands, and learns from human motion and interaction.
Ph.D. student at ShanghaiTech University. I turn LiDAR, cameras, physical robots, and people into systems that can learn together.
HUMAN-CENTRIC
AI
Research with a physical point of view.
ReMoGen
Real-time reactions for interactive agents, learned across people and environments.
SymBridge
Interactive human-robot symbiosis that closes the real-to-sim loop.
UniPVU-Human
Human-centric point cloud video understanding without the usual complexity.
FusionPose
Weakly supervised human pose estimation across cameras and LiDAR.
Human behavior is not noise. It is the signal.
My work studies how intelligent agents can perceive dynamic people and spaces, learn from human feedback, and act in a way that is useful rather than merely automated.
That shows up in 3D perception, multimodal fusion, interactive datasets, embodied learning, and human-robot collaboration.