3 papers
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.LG2026
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…
cs.CL2025
DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue
Feiyuan Zhang, Dezhi Zhu, James Ming +6
Retrieval-Augmented Generation (RAG) systems have shown substantial benefits in applications such as question answering and multi-turn dialogue \citep{lewis2020retrieval}. However,…