Sheng Xu

About

I’m a second year PhD student at the School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-SZ) supervised by Prof. Guiliang Liu and co-supervised by Prof. Hongyuan Zha.
Before, I received my Bachelor degree (rank: 1/225) at the School of Computer Science, Northwestern Polytechnical University (NWPU) in 2023.
My research focuses on:

[07/2024] One book chapter was under processing by the editor.
[06/2024] One paper was accepted to ICML 2024 Workshop MHFAIA.
[05/2024] One paper was accepted to ICML 2024.
[01/2024] Two papers were accepted to ICLR 2024.
[07/2023] I graduated from NWPU with the honor of Outstanding Graduate of Shaanxi Province (top 1%) and Excellent Graduation Thesis (top 5%).

Conference Paper

Uncertainty-aware Preference Alignment in Reinforcement Learning from Human Feedback
Sheng Xu, Bo Yue, Hongyuan Zha, Guiliang Liu.
ICML Workshop on Models of Human Feedback for AI Alignment (MHFAIA@ICML), 2024
[Paper], [Code (coming soon)]

Robust Inverse Constrained Reinforcement Learning under Model Misspecification
Sheng Xu, Guiliang Liu.
International Conference on Machine Learning (ICML), 2024
[Paper], [Code]

Uncertainty-aware Constraint Inference in Inverse Constrained Reinforcement Learning
Sheng Xu, Guiliang Liu.
International Conference on Learning Representations (ICLR), 2024
[Paper], [Code]

Enhancing Human-AI Collaboration Through Logic-Guided Reasoning
Chengzhi Cao, Yinghao Fu, Sheng Xu, Ruimao Zhang, Shuang Li.
International Conference on Learning Representations (ICLR), 2024
[Paper], [Code]

An Improved Lightweight YOLOv5 Model Based on Attention Mechanism for Face Mask Detection
Sheng Xu, Zhanyu Guo, Yuchi Liu, Jingwei Fan, Xuxu Liu.
International Conference on Artificial Neural Networks (ICANN), 2022
[Paper], [Code]

Book Chapter

Risk, Reward, and Reinforcement Learning in Ice Hockey Analytics
Sheng Xu, Oliver Schulte, Yudong Luo, Pascal Poupart, Guiliang Liu.
Book Chapter in Artificial Intelligence and Machine Learning in Sports Science, Springer, 2024
[Paper (draft version)]

Outstanding Graduate of Shaanxi Province, Education Department of Shaanxi Provincial Government, 2023
NWPU Top Undergraduate Student Award (highest honor of undergraduates, only 10 winners), 2022
NWPU Top Class Scholarship (only 10 winners) 2022
National Scholarship (top 1%), 2022 & 2021
Modern Scientists Scholarship (top 1%), 2022
Huawei Scholarship (top 1%), 2022
Meritorious Winner, Mathematical Contest In Modeling, 2022
First Prize, "Challenge Cup" Competition, 2022

“Robust Inverse Constrained Reinforcement Learning under Model Misspecification”.
Invited Talk at RLChina Paper Seminar. [Video (in Chinese)]