Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
URNet: Uncertainty-aware Refinement Network for Event-based Stereo Depth Estimation accepted by Visual Intelligence.
I2EKD: Efficient and Versatile Image-to-Event Knowledge Distillation accepted by TCSVT.
CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving accepted by ICCV 2025.
Feature-aligned Fisheye Object Detection accepted by IROS 2025.
TUMTraffic-VideoQA accepted by ICML 2025.
Served as an Associate Editor of the journal Visual Intelligence.
Served as the Forum Chair of the China Embodied AI Conference 2025: Special Forum-Embodied Manipulation and Continuous Learning.
Joined the Editorial Board of the journal Artificial Intelligence and Autonomous Systems (AIAS).
Served as the Chair of the Germany Forum of the 6th Sino-German Symposium on Intelligent Robots.
Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning accepted by ACCV 2024.
BiSeg-SAM accepted by IEEE BIBM 2024.
Swin-Unet ranked top 3 most cited ECCV papers in five years in Google Metrics.
A paper on 4-DOF point cloud registration accepted by IEEE TPAMI.
Two papers on RGB-Event fusion object detection and dataset distillation accepted by ECCV 2024.
A paper on lightweight fisheye object detection accepted by IROS 2024.
Organizing a special issue on 'Advanced Perception and Planning Technology in Robotics' for Frontiers in Robotics and AI (SCI).
A paper on dimension-pooling transformer for semantic segmentation accepted by IEEE TITS.
A paper on vision language models in autonomous driving accepted by IEEE TIV.
A paper on point cloud registration accepted by IEEE TIV.
Research Experience
Currently a Postdoctoral Research Associate at the Chair of Robotics, AI, and Real-Time Systems, Technical University of Munich (TUM).
Education
Ph.D. from Technical University of Munich (TUM), supervised by Prof. Alois Knoll.
Background
Research interests focus on vision and language models for scene understanding, including autonomous driving, robotic grasping, medical image analysis, and dense prediction (classification, detection, and segmentation).
Miscellany
Looking for highly self-motivated collaborators who are interested in autonomous driving, robotic grasping, medical image analysis, and dense prediction. Please send an up-to-date resume via email.