Xiaowei Chi

4

Papers

16

Total Citations

Papers (4)

PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents

VideoVAE+: Large Motion Video Autoencoding with Cross-modal Video VAE

Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation