Xin Yan

4

Papers

8

Total Citations

Papers (4)

Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation

RapVerse: Coherent Vocals and Whole-Body Motion Generation from Text

ContPhy: Continuum Physical Concept Learning and Reasoning from Videos

3D-VLA: A 3D Vision-Language-Action Generative World Model