Mengda Xu
Scholar

Mengda Xu

Google Scholar ID: K1_MygkAAAAJ
Stanford University; Columbia University
RoboticsComputer Vision
Citations & Impact
All-time
Citations
362
 
H-index
7
 
i10-index
6
 
Publications
14
 
Co-authors
0
 
Resume (English only)
Academic Achievements
  • DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation (Preprint, 2025)
  • Flow as the Cross-Domain Manipulation Interface (8th Conference on Robot Learning (CoRL 2024), X-Embodiment Workshop (CoRL 2024), Best Paper Finalist)
  • XSkill: Cross Embodiment Skill Discovery (7th Conference on Robot Learning (CoRL 2023))
  • O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models (First Conference on Language Modeling (COLM 2024))
  • ASPiRe: Adaptive Skill Priors for Reinforcement Learning (36th Conference on Neural Information Processing Systems (NeurIPS 2022))
Research Experience
  • Member of the Robotics & Embodied Artificial Intelligence Lab (REAL) @ Stanford.
Education
  • PhD in Computer Science from Stanford University, co-advised by Professor Shuran Song and Professor Manuela Veloso.
Background
  • PhD student in Computer Science at Stanford University, with a broad interest in robotic manipulation.
Miscellany
  • No personal interests mentioned.
Co-authors
0 total
Co-authors: 0 (list not available)