2 papers
cs.LG2026
MoE Proxy Models for Low-Cost Failure Reproduction and Diagnosis in LLM RL Post-Training
Yikai Wang, Chuansai Zhou, Yuhang Zhou +10
Reinforcement learning (RL) post-training of large language models (LLMs) is computationally intensive and involves complex system pipelines with substantial debugging overhead. In…
cs.LG2025
MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Cluster
Laingjun Feng, Chenyi Pan, Xinjie Guo +11
Reinforcement learning (RL) is a paradigm increasingly used to align large language models. Popular RL algorithms utilize multiple workers and can be modeled as a graph, where each…