Mingyu Chen

activity

20232026

collaborators

Showing 2025Show all

2 papers · 1 filter

cs.LG2025

Accelerating RL for LLM Reasoning with Optimal Advantage Regression

Kianté Brantley, Mingyu Chen, Zhaolin Gao +4

Reinforcement learning (RL) has emerged as a powerful tool for fine-tuning large language models (LLMs) to improve complex reasoning abilities. However, state-of-the-art policy opt…

cs.LG2025

Avoiding $exp (R_{max})$ scaling in RLHF through Preference-based Exploration

Mingyu Chen, Yiding Chen, Wen Sun +1

Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for large language model (LLM) alignment. This paper studies the setting of online RLHF and foc…

Accelerating RL for LLM Reasoning with Optimal Advantage Regression

Avoiding exp(Rmax​) scaling in RLHF through Preference-based Exploration

Avoiding $exp (R_{max})$ scaling in RLHF through Preference-based Exploration