qizekun/OmniSpatial
Preview
•
Updated
•
209
•
15
Zekun Qi
qizekun
AI & ML interests
Embodied Intelligence, Large Langugae Model, 3D Computer Vision
Recent Activity
upvoted
a
paper
2 days ago
Learning Humanoid End-Effector Control for Open-Vocabulary Visual Loco-Manipulation
upvoted
a
paper
10 days ago
VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
upvoted
a
paper
17 days ago
3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation
Organizations
