Scholar
Yexin Li
Google Scholar ID: 8Sof7boAAAAJ
State Key Laboratory of General Artificial Intelligence BIGAI
reinforcement learning
multi-agent system
multi-armed bandits
data mining
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
818
H-index
9
i10-index
9
Publications
20
Co-authors
3
list available
Contact
Email
liyexin@bigai.ai
CV
Open ↗
GitHub
Open ↗
Publications
19 items
Train Ahead, Distill Back: Bootstrapping On-Policy Self-Distillation for Large Language Models
2026
Cited
0
From Judgment Quality to Downstream Utility: Rethinking LLM-as-a-Judge for Open-Ended Tasks
2026
Cited
0
REARL: A Closed-loop Autonomous Driving Simulation Enhancement Framework with Real Traffic Data and Large Language Models
2026
Cited
0
SAGA: Scene-Aware, Goal-Evolving Agents for Long-Horizon CivRealm Strategy Planning
2026
Cited
0
Black-Box Continual Learning for Vision-Language Models
2026
Cited
0
Hierarachical Multiagent Reinforcement Learning for Multi-Group Tax Game
2026
Cited
0
Large Language Models Explore by Latent Distilling
2026
Cited
0
IDER: IDempotent Experience Replay for Reliable Continual Learning
2026
Cited
0
Load more
Co-authors
3 total
Yu Zheng (郑宇)
Vice President of JD.COM, Chief Data Scientist of JD Tech., Head of JD Intelligent Cities Research
Qiang Yang (杨强）
Hong Kong Polytechnic University, Emeritus(Chair Prof. HKUST, CAIO WeBank), IJCAI President 2017-19
Siyuan Qi
Gyges Labs
