Mingyu Chen

About Me

Hi! I am a first second third fourth year Ph.D. student in the Department of Electrical & Computer Engineering at Boston University. I am fortunate to work with Prof. Xuezhou Zhang. Prior to this, I obtained my bachelor’s degree from Huazhong University of Science and Technology.

My research lies in the areas of Reinforcement Learning, Online Learning, Bandits and Optimization. Currently my focus is in making Interactive Decision Making process parameter-free and scale-free, and developing efficient and unified algorithms for scientific and engineering applications.

Research Interests

• Reinforcement Learning
• RLHF
• LLM reasoning
• RL theory

News

• [Sep. 2025] Our work “Avoiding exp(R) scaling in RLHF through Preference-based Exploration” is accepted at NeurIPS 2025!

• [Sep. 2025] Our work “Accelerating RL for LLM Reasoning with Optimal Advantage Regression” is accepted at NeurIPS 2025!

• [Sep. 2024] Our work “State-free Reinforcement Learning” is accepted at NeurIPS 2024!

• [May 2024] Our work “Scale-free Adversarial Reinforcement Learning” is accepted at COLT 2024!

• [Aug. 2023] Our CDC 2022 paper “Scheduling and pricing non-preemptive electric loads: A convex approach” is selected for the Best Paper Prize by the Energy Systems Technical Committee (formerly the Smart Grid TC) of the IEEE Control Systems Society (CSS).

Publications

Services

Conference Reviewers

• Neural Information Processing Systems (NIPS) 2023
• International Conference on Learning Representations (ICLR) 2024

Powered by Jekyll and Minimal Light theme.