Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Le Xu

Le Xu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2Distributed×1ML×1

Frequent co-authors

Gangmuk Lim1×
Wanyu Zhao1×
Brighten Godfrey1×
Jiaxin Shan1×
Liguang Xie1×
Yang Li1×

Research Timeline

2026
CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPO

The paper proposes CAST, an answer-free self-distillation method that enhances Group Relative Policy Optimization (GRPO) for verifiable rewards, allowing token-level advantage signals even when all sampled trajectories are uniformly correct or incorrect.

Lodestar: An Online-Learning LLM Inference Router

Lodestar is a novel online learning-based request routing system that significantly improves LLM inference efficiency by dynamically assigning incoming requests to the optimal GPU instance to minimize latency.

Highlighted terms show continued research focus across papers

Papers

cs.DCcs.AIcs.LGRecentMay 31, 2026

Lodestar: An Online-Learning LLM Inference Router

Gangmuk Lim, Wanyu Zhao, Brighten Godfrey, Jiaxin Shan +2 more

Lodestar is a novel online learning-based request routing system that significantly improves LLM inference efficiency by dynamically assigning incoming requests to the optimal GPU instance to minimize…

View →
cs.AIRecentMay 29, 2026

CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPO

Yang Li, Gongle Xue, Yijia Guo, Yuheng Yuan +2 more

The paper proposes CAST, an answer-free self-distillation method that enhances Group Relative Policy Optimization (GRPO) for verifiable rewards, allowing token-level advantage signals even when all sa…

View →