Che Xu

Researcher, Peking University

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

1 paper

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model

#2405 Spotlight · Zhe Li, Xiang Bai, Jieyu Zhang, Zhuangzhe Wu, Che Xu, Ying Li, Chengkai Hou, Shanghang Zhang

URDF-Anything is an end-to-end MLLM-based framework that jointly optimizes geometric segmentation and kinematic prediction for articulated object reconstruction.