Scholar
Lei Yuan
Google Scholar ID: kbDU8bEAAAAJ
Nanjing University
Citations & Impact
Citations
671
H-index
15
i10-index
20
Publications
20
Co-authors
6
list available
Contact
No contact links provided.
Publications
Resume (English only)
Academic Achievements
- Published multiple papers, including:
- - Multi-agent Embodied AI: Advances and Future Directions (2025)
- - A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environment (2024)
- - Multi-agent In-context Coordination via Decentralized Memory Retrieval (AAAI 2026)
- - Uncertainty-Sensitive Privileged Learning (NeurIPS 2025)
- - Adaptable Safe Policy Learning from Multi-task Data with Constraint Prioritized Decision Transformer (NeurIPS 2025)
- - Multi-Agent Imitation by Learning and Sampling from Factorized Soft Q-Function (NeurIPS 2025)
- - Sequential Multi-Agent Dynamic Algorithm Configuration (NeurIPS 2025)
- - LLM-Assisted Semantically Diverse Teammate Generation for Efficient Multi-agent Coordination (ICML-25)
- - Learning to Reuse Policies in State Evolvable Environments (ICML-25)
- - Efficient Multi-agent Offline Coordination via Diffusion-based Trajectory Stitching (ICLR 2025)
- - Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation (ICLR 2025)
- - SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks (AAAI 2025)
- - Multi-Agent Domain Calibration with a Handful of Offline Data (NeurIPS 2024)
Research Experience
- Working in the LAMDA RL Lab with Prof. Yang Yu and looking for self-motivated students for research on the above-mentioned research interests.
Education
- Obtained Ph.D. degree from the Department of Computer Science and Technology at Nanjing University in December 2023, advised by Prof. Yang Yu.
Background
- Currently an assistant researcher in the School of Artificial Intelligence at Nanjing University and a member of the LAMDA Group. Research interests include Interactive Intelligence and Reinforcement Learning, particularly in Multi-agent Systems, Embodied AIs, Large Decision Models, Sim2Real, Human-AI Interaction and Coordination, and Large Language Models and their applications.
