Wenqiao Li

李文峤

School of Artificial Intelligence, Shanghai Jiao Tong University

I am a Ph.D. student at the School of Artificial Intelligence, SJTU, advised by Dr. Siyuan Huang, Prof. Chuan Wen, and Dr. Tengyu Liu. During my master's studies, I was supervised by Prof. Yingna Wu and Prof. Shenghua Gao. I am also a Student Researcher at Sharpa and the Beijing Institute for General AI, working on dexterous manipulation through full-stack solutions.

My research interests lie in dexterous manipulation and robot perception. My long-term goal is to make robots more useful. I am currently focusing on dexterous manipulation, tactile sensing, exoskeletons, and representation learning.

Research

UVTA: Unified Visual-Tactile-Action Modeling from Human Demonstrations for Dexterous Manipulation

Wenqiao Li, Qianyou Zhao, Jiawen Hao, Xuezhou Zhu, Tengyu Liu, Kaifeng Zhang, Chuan Wen, Siyuan Huang

arXiv, 2026

Learning contact-aware dexterous manipulation from human visual-tactile demonstrations through joint action and tactile prediction.

DexEMG: Towards Dexterous Teleoperation System via EMG2Pose Generalization

Qianyou Zhao, Wenqiao Li, Chiyu Wang, Kaifeng Zhang

IROS, 2026

A lightweight dexterous teleoperation system that maps muscle activity to hand poses and robot actions.

PASDF pose-wise alignment and signed distance field architecture

Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric Representation

Bozhong Zheng, Jinye Gan, Xiaohao Xu, Xintao Chen, Wenqiao Li, Xiaonan Huang, Na Ni, Yingna Wu

ICCV, 2025

Continuous, pose-aware shape representations for precise 3D anomaly localization and geometric repair.

MulSen-AD RGB, infrared, and point-cloud memory banks and Decision Gating Unit

Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Properties

Wenqiao Li, Bozhong Zheng, Xiaohao Xu, Jinye Gan, Fading Lu, Xiang Li, Na Ni, Zheng Tian, Xiaonan Huang, Shenghua Gao, Yingna Wu

CVPR, 2025

Combining RGB, 3D geometry, and infrared thermography to detect both external and internal object defects.

Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detection

Wenqiao Li, Yao Gu, Xintao Chen, Xiaohao Xu, Ming Hu, Xiaonan Huang, Yingna Wu

CVPR, 2025

Reasoning about physical anomalies from video dynamics and interaction outcomes through real-time robot–object interaction.

IMRNet training and testing architecture for 3D anomaly detection

Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network

Wenqiao Li, Xiaohao Xu, Yao Gu, Bozhong Zheng, Shenghua Gao, Yingna Wu

CVPR, 2024

Synthetic 3D anomalies and iterative masked reconstruction for scalable point-cloud anomaly detection.

Academic Service: Reviewer for CVPR, NeurIPS, ECCV, ACM MM, IEEE TMM, and other venues.