Qisen Yang

Qisen Yang

PhD Candidate of Artificial Intelligence

Tsinghua University

Biography

I’m Qisen Yang (杨琪森 in Chinese), a Ph.D. student at Tsinghua University, advised by Prof. Gao Huang and Prof. Shiji Song. My research interests include LLMs for social science, foundation models for decision making, offline reinforcement learning, interpretable RL, and efficient deep learning techniques.
🔥I’m on job market now!
🔥If you are interested in me, please contact me via yangqs19@mails.tsinghua.edu.cn.

Interests
  • Reinforcement Learning
  • Foundation models
  • LLMs for Social Science
  • Computer Vision
Education

  • Ph.D. Student in Artificial Intelligence, 2019 - Present

    Tsinghua University

  • B.S. in Psychology, 2016 - 2019

    Tsinghua University

  • B.E. in Precision Instrument, 2015 - 2019

    Tsinghua University

News

2023-09 One paper accepted by NeurIPS 2023 as Spotlight !
State-Adaptive Balances for Offline-to-Online Reinforcement Learning Sep 2023
2023-08 One paper accepted by IEEE TSMC !
Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning Aug 2023
2023-07 One paper accepted by IEEE TNNLS !
Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance Jul 2023
2023-04 One paper accepted by ICML 2023 !
Boosting Offline Reinforcement Learning with Action Preference Query Apr 2023
2022-09 One paper accepted by NeurIPS 2022 as Spotlight !
Efficient Knowledge Distillation from Model Checkpoints Sep 2022

Publications

Qisen Yang, Zekun Wang, Honghui Chen, Shenzhi Wang, Yifan Pu, Xin Gao, Wenhao Huang, Shiji Song, Gao Huang (2024). LLM Agents for Psychology: A Study on Gamified Assessments. Arxiv preprint.

PDF Cite Arxiv

Shenzhi Wang, Qisen Yang, Jiawei Gao, Matthieu Gaetan Lin, Hao Chen, Liwei Wu, Ning Jia, Shiji Song, Gao Huang (2023). Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning. In NeurIPS.

PDF Cite Arxiv

Qisen Yang, Huanqian Wang, Mukun Tong, Wenjie Shi, Gao Huang, Shiji Song (2023). Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning. In IEEE TSMC.

PDF Cite Arxiv

Qisen Yang, Shenzhi Wang, Qihang Zhang, Gao Huang, Shiji Song (2023). Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance. In IEEE TNNLS.

PDF Cite Arxiv

Qisen Yang, Shenzhi Wang, Matthieu Gaetan Lin, Shiji Song, Gao Huang (2023). Boosting Offline Reinforcement Learning with Action Preference Query. In ICML.

PDF Cite Arxiv

See all publications

Experience

 
 
 
 
 
Counselor for Undergraduate Students
Tsinghua University
August 2019 – June 2021

Responsibilities include:

  • Managed student adaptation, personal development, conflict resolution, and team organization.
  • Addressed critical cases, including suicide prevention, dropout risk, and support for marginalized students.
 
 
 
 
 
Consultant
Tsinghua University Learning Development Center
August 2021 – Present
Assisted students from various departments, offering guidance on academic challenges, personal growth, and minor mental health issues.
 
 
 
 
 
Reviewer for ICML, NeurIPS, ICRA, and so on.
IEEE Computer Society
August 2019 – Present

Awards

  • National Scholarship, Ministry of Education of China, 2023.
  • Excellent Student Leader, Tsinghua University, 2020.
  • Outstanding Undergraduate Thesis Award, Tsinghua University, 2019.
  • National Scholarship, Ministry of Education of China, 2017.

    Contact

    I’m always open to exploring interesting ideas and collaborations!