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

Ruihang Lai

2 indexed papers

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

Publications per year

2
26

Top categories

ML×2AI×2NLP×2Distributed×2

Frequent co-authors

Hao Kang2×
Haozhan Tang2×
Akaash R. Parthasarathy2×
Zichun Yu2×
Junru Shao2×
Todd C. Mowry2×

Research Timeline

2026
PithTrain: A Compact and Agent-Native MoE Training System

The paper introduces PithTrain, a compact, agent-native Mixture-of-Experts (MoE) training framework that significantly improves agent-task efficiency compared to existing production stacks.

PithTrain: A Compact and Agent-Native MoE Training System

The paper introduces PithTrain, a compact, agent-native Mixture-of-Experts (MoE) training framework that significantly improves agent-task efficiency compared to existing production stacks.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.CLRecentMay 29, 2026

PithTrain: A Compact and Agent-Native MoE Training System

Ruihang Lai, Hao Kang, Haozhan Tang, Akaash R. Parthasarathy +5 more

The paper introduces PithTrain, a compact, agent-native Mixture-of-Experts (MoE) training framework that significantly improves agent-task efficiency compared to existing production stacks.

View →
cs.LGcs.AIcs.CLRecentMay 29, 2026

PithTrain: A Compact and Agent-Native MoE Training System

Ruihang Lai, Hao Kang, Haozhan Tang, Akaash R. Parthasarathy +5 more

The paper introduces PithTrain, a compact, agent-native Mixture-of-Experts (MoE) training framework that significantly improves agent-task efficiency compared to existing production stacks.

View →