arxiv:2511.13719
Zhongang Cai
caizhongang
AI & ML interests
Multimodal, Spatial Intelligence, Embodied AI, Virtual Humans.
Recent Activity
upvoted
a
paper
3 days ago
Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition
upvoted
a
paper
14 days ago
DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
updated
a model
21 days ago
caizhongang/SMPLer-X