11 papers
Predictive Divergence Masks for LLM RL
Xiangxin Zhou, Jiarui Yao, Penghui Qi +4
Reinforcement learning for large language models (LLMs) typically relies on trust-region masks to stabilize off-policy updates. The dominant PPO-style approach uses the sampled-tok…
Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models
Bowen Ping, Xiangxin Zhou, Penghui Qi +3
Recent work has demonstrated that online reinforcement learning (RL) can substantially improve the quality and alignment of flow matching models for image and video generation. Met…
Rethinking the Trust Region in LLM Reinforcement Learning
Penghui Qi, Xiangxin Zhou, Zichen Liu +4
Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorith…
Rethinking the Divergence Regularization in LLM RL
Jiarui Yao, Xiangxin Zhou, Penghui Qi +3
Reinforcement learning (RL) has become a key component of post-training large language models (LLMs). In practice, LLM RL is often off-policy because of training-inference mismatch…
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
Bo Liu, Leon Guertler, Simon Yu +9
Recent advances in reinforcement learning have shown that language models can develop sophisticated reasoning through training on tasks with verifiable rewards, but these approache…
Revisiting Parameter Server in LLM Post-Training
Xinyi Wan, Penghui Qi, Guangxing Huang +3
Modern data parallel (DP) training favors collective communication over parameter servers (PS) for its simplicity and efficiency under balanced workloads. However, the balanced wor…