15 citations · 49 across the 17 of their papers we have counts for
4 papers · 1 filter
TrainBridge: Agentic NPU Training Optimization Guided by GPU Compilation Evidence
Yupeng Chen, Kunxiang Zhao, Xingjian Wang +6
We study how to improve training efficiency on Ascend NPUs. In the NPU training programs we study, framework-level compilation optimizations such as operator fusion are only partia…
Towards Better Training Signal: Advantage Clipped Policy Optimization
Ruichuan Huang, Jinghan Liu, Congliang Chen
Reinforcement learning (RL) has become a cornerstone for improving the reasoning capabilities of large language models (LLMs), but the need for on-policy data substantially limits…
Off-Policy Value-Based Reinforcement Learning for Large Language Models
Peng-Yuan Wang, Ziniu Li, Tian Xu +8
Improving data utilization efficiency is critical for scaling reinforcement learning (RL) for long-horizon tasks where generating trajectories is expensive. However, the dominant R…
Adam Converges Without Any Modification On Update Rules
Yushun Zhang, Bingran Li, Congliang Chen +2
Adam is the default algorithm for training neural networks, including large language models (LLMs). However, \citet{reddi2019convergence} provided an example that Adam diverges, ra…