collaborators

5 papers

cs.CL2025

REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization

Jian Hu, Jason Klein Liu, Haotian Xu +1

Reinforcement Learning from Human Feedback~(RLHF) plays a crucial role in aligning Large Language Models~(LLMs). The dominant algorithm, Proximal Policy Optimization~(PPO), employs…

cs.AI2025

OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Jian Hu, Xibin Wu, Wei Shen +12

Large Language Models (LLMs) fine-tuned via Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) significantly improve the al…

cs.LG2025

Rethinking KL Regularization in RLHF: From Value Estimation to Gradient Optimization

Kezhao Liu, Jason Klein Liu, Mingtao Chen +1

Reinforcement Learning from Human Feedback (RLHF) leverages a Kullback-Leibler (KL) divergence loss to stabilize training and prevent overfitting. However, in methods such as GRPO,…

cs.AI2025

AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence

Yuliang Liu, Junjie Lu, Zhaoling Chen +10

Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefin…

cs.LG2025

LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs

Yunhui Xia, Wei Shen, Yan Wang +5

We introduce LeetCodeDataset, a high-quality benchmark for evaluating and training code-generation models, addressing two key challenges in LLM research: the lack of reasoning-focu…