3 papers
cs.LG2026
When Do Larger Batches Help Scale LLM Reinforcement Learning?
Ziniu Li, Jinbo Wang, Guanhua Huang +3
Larger batches reduce the variance of stochastic gradients per update and are therefore often expected to accelerate training. Yet whether this statistical benefit translates into…
cs.DC2026
Schedule-Level Shared-Prefix Reuse for LLM RL Training
Pengbo Li, Feiyuan Zhang, Guangming Sheng +7
GRPO-based LLM post-training commonly samples multiple trajectories from the same prompt and then trains on the resulting group. In long-context GRPO workloads, this shared prompt-…
cs.LG2025
Unlocking Full Efficiency of Token Filtering in Large Language Model Training
Di Chai, Pengbo Li, Feiyuan Zhang +7
Token filtering has been proposed to enhance the utility of large language models (LLMs) by eliminating inconsequential tokens during training. While usingfewer tokens is expected…