Yu Shen

Ph.D. student, Computer Science at University of Maryland, College Park

Yu Shen, a Ph.D. student majoring in Computer Science at the University of Maryland. His research interests are AI technologies like computer vision, 3D perception, multi-modality learning, robust learning, etc., in real-world applications like autonomous driving, AR/VR/Metaverse, virtual try-on, etc. Previously, he worked for Tencent, DJI, and Hiscene, and interned at Microsoft, Bytedance, Baidu, Amazon, Adobe. His working experiences mainly focus on vision-based/lidar-based 3D perception, like SLAM, VIO, 3D object/2D image recognition/tracking with 3D pose estimation, etc. His Ph.D. advisor is Prof. Ming C. Lin.

Email: yushen at umd dot edu

Curriculum Vitae

Task-Driven Domain-Agnostic Learning with Information Bottleneck for Autonomous Steering

Yu Shen, Laura Zheng, Tianyi Zhou, and Ming C. Lin

ICRA 2024

Collaborative Decision-Making Using Spatiotemporal Graphs in Connected Autonomy

Peng Gao, Yu Shen, Ming C. Lin

ICRA 2024

Auxiliary Modality Learning with Generalized Curriculum Distillation

Yu Shen, Xijun Wang, Peng Gao, and Ming C. Lin

ICML 2023

Small-shot Multi-modal Distillation for Vision-based Autonomous Steering

Yu Shen, Luyu Yang, Xijun Wang, and Ming C. Lin

ICRA 2023

Visual, Spatial, Geometric-Preserved Place Recognition for Cross-View and Cross-Modal Collaborative Perception

Peng Gao, Jing Liang, Yu Shen, Sanghyun Son, Ming C. Lin

IROS 2023 (Best Paper Award)

Inverse Reinforcement Learning with Hybrid Weight Tuning and Trust Region Optimization for Autonomous Maneuvering

Yu Shen, Weizi Li, and Ming C. Lin

IROS 2022

Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering

Yu Shen, Laura Zheng, Manli Shu, Weizi Li, Tom Goldstein, and Ming C. Lin

NIPS 2021

Adversarial Differentiable Data Augmentation for Autonomous Systems

Manli Shu, Yu Shen, Ming C. Lin, and Tom Goldstein

ICRA 2021

[paper]

GAN-based Garment Generation Using Sewing Pattern Images

Yu Shen, Junbang Liang, and Ming C. Lin

ECCV 2020