Published several papers including 'NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions', 'CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model', etc. Among them, 'CheckManual: A New Challenge and Benchmark for Manual-based Appliance Manipulation' was accepted by CVPR 2025 and highlighted, 'Improving Situated Conversational Agents with Step-by-Step Multi-modal Logic Reasoning' won the Best Paper award at DSTC 11 Workshop.
Research Experience
Involved in multiple research projects such as NavSpace, CorrectNav, CheckManual, etc.
Education
PhD candidate at the Center on Frontiers of Computing Studies (CFCS), Peking University, advised by Prof. Hao Dong; Bachelor's and Master's degrees from Beijing University of Posts and Telecommunications (BUPT).
Background
Research interests include robot manipulation and embodied navigation.
Miscellany
Reviewer for several conferences including RAL 2025, ACM MM 2023, NeurIPS 2023.