activity
20232026
collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective

Yuheng Zhang, Chenlu Ye, Shuowei Jin +4

Reinforcement learning, including reinforcement learning with verifiable rewards (RLVR), has emerged as a powerful approach for LLM post-training. Central to these approaches is th…

cs.LG2025

Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL Objectives

Wei Xiong, Chenlu Ye, Baohao Liao +6

Reinforcement learning (RL) for large language model reasoning is frequently hindered by signal loss, a phenomenon where standard uniform sampling with small group sizes fails to u…

cs.LG2025

Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL

Jiarui Yao, Yifan Hao, Hanning Zhang +4

Chain-of-thought (CoT) reasoning in large language models (LLMs) can be formalized as a latent variable problem, where the model needs to generate intermediate reasoning steps. Whi…

cs.LG2025

A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce

Wei Xiong, Jiarui Yao, Yuhui Xu +8

Reinforcement learning (RL) has become a prevailing approach for fine-tuning large language models (LLMs) on complex reasoning tasks. Among recent methods, GRPO stands out for its…

cs.LG2025

Improving LLM General Preference Alignment via Optimistic Online Mirror Descent

Yuheng Zhang, Dian Yu, Tao Ge +5

Reinforcement learning from human feedback (RLHF) has demonstrated remarkable effectiveness in aligning large language models (LLMs) with human preferences. Many existing alignment…

cs.LG2024

Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning

Yuheng Zhang, Dian Yu, Baolin Peng +6

Reinforcement Learning with Human Feedback (RLHF) has achieved great success in aligning large language models (LLMs) with human preferences. Prevalent RLHF approaches are reward-b…