Donglai Xiang

9

Papers

206

Total Citations

Papers (9)

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

Articulated Kinematics Distillation from Video Diffusion Models

PartField: Learning 3D Feature Fields for Part Segmentation and Beyond

Semantic Object Parsing With Local-Global Long Short-Term Memory

Monocular Total Capture: Posing Face, Body, and Hands in the Wild

You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions

Surface Normals in the Wild

Single-Network Whole-Body Pose Estimation

Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation