7 citations · 7 across the 10 of their papers we have counts for
11 papers · 1 filter
Staleness-Learning Rate Scaling Laws for Asynchronous RLHF
Jingwei Song, Haofeng Xu, Jie Xiao +8
High-throughput RLHF systems often decouple rollout generation from policy optimization, leading to the use of stale rollouts during learner updates. In this work, we study the eff…
Step-TP: A Grounded, Step-Level Dataset with Chain-of-Thought Reasoning for LLM-Guided Tensor Program Optimization
Mengfan Liu, Da Zheng, Junwei Su +1
Despite the strong reasoning capabilities of large language models (LLMs), optimizing the execution efficiency of tensor programs remains challenging due to the need for precise, c…
GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control
Haofeng Xu, Junwei Su, Yukun Tian +3
Asynchronous execution is essential for scaling reinforcement learning (RL) to modern large model workloads, including large language models and AI agents, but it can fundamentally…
Full-Graph vs. Mini-Batch Training: Comprehensive Analysis from a Batch Size and Fan-Out Size Perspective
Mengfan Liu, Da Zheng, Junwei Su +1
Full-graph and mini-batch Graph Neural Network (GNN) training approaches have distinct system design demands, making it crucial to choose the appropriate approach to develop. A cor…
A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations
Junwei Su, Chuan Wu
Score-based graph generative models (SGGMs) have proven effective in critical applications such as drug discovery and protein synthesis. However, their theoretical behavior, partic…
On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks
Junwei Su, Chuan Wu
This paper studies the interplay between learning algorithms and graph structure for graph neural networks (GNNs). Existing theoretical studies on the learning dynamics of GNNs pri…