Scholar
Qiang HE
Google Scholar ID: l6Y2ZDYAAAAJ
Ruhr University Bochum
Citations & Impact
Citations
132
H-index
7
i10-index
5
Publications
14
Co-authors
4
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Selected Publications:
- - Pareto Multi-Objective Alignment for Language Models (ECML/PKDD 2025)
- - Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment (ICML 2024)
- - Two papers accepted to ICLR 2024, one of which is a spotlight paper.
Research Experience
- Currently on the job market. Reviewer for ICLR, NeurIPS, ICML, AAAI, DMLR, ICPR.
Education
- Currently a fourth-year PhD student at Ruhr-University Bochum, supervised by Prof. Dr. Setareh Maghsudi. Master's degree in Theory and Method of Artificial Intelligence from the Institute of Automation, Chinese Academy of Sciences.
Background
- Research Interests: Large Language Models, RLHF, Human-AI Alignment, Game AI, Reinforcement Learning. Currently, my research aims to i) develop controllable AI in both training and inference/adaptation; ii) theory and real-world application of Human-AI alignment; and iii) understand the structural information of LLMs, RLHF & RL and how to leverage it to enable agent performance.
Miscellany
- Contact Information:
- - Email: qianghe97 AT gmail DOT com, Qiang DOT He AT rub DOT de
- - WeChat ID: pposac
