Xu He

4

Papers

28

Total Citations

Papers (4)

Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model

TAPNext: Tracking Any Point (TAP) as Next Token Prediction

MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement

Improving Unsupervised Hierarchical Representation with Reinforcement Learning