Chengdong Ma
Scholar

Chengdong Ma

Google Scholar ID: 8J0OzuAAAAAJ
Peking University
Reinforcement LearningMulti-Agent Systems
Citations & Impact
All-time
Citations
204
 
H-index
7
 
i10-index
6
 
Publications
19
 
Co-authors
13
list available
Resume (English only)
Academic Achievements
  • Published in Nature Machine Intelligence: 'Efficient and Scalable Reinforcement Learning for Large-scale Network Control', covered by Xinhua Net, Science and Technology Daily, and Peking University News
  • ICLR 2025: 'Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment'
  • AAMAS 2025: 'Mean Field Correlated Imitation Learning'
  • NeurIPS 2024: 'Panacea: Pareto Alignment via Preference Adaptation for LLMs'
  • Arxiv 2023: 'Evolving Diverse Red-team Language Models in Multi-round Multi-agent Games'
  • Co-instructor for ICML 2025 Tutorial: 'Alignment Methods for Language Models: A Machine Learning Perspective'
  • Invited talks in 2024 at the Distributed Artificial Intelligence (DAI) conference, National Key Lab of Autonomous Intelligent Unmanned Systems (BIT), and Cognitive Computing and Reasoning Lab (BIGAI)