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

Daniel Amir

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Networking×1

Frequent co-authors

Ori Cohen1×
Jakob Krebs1×
Mark Silberstein1×

Research Timeline

2026
MoX: Efficient MoE Routing on Direct-Connect Topologies

This paper proposes MoX, an optimized load-oblivious routing method for efficient training and inference of sparse Model-of-Experts (MoE) on static direct-connect fabrics.

Highlighted terms show continued research focus across papers

Papers

cs.NIEmpiricalRecentJul 22, 2026

MoX: Efficient MoE Routing on Direct-Connect Topologies

Ori Cohen, Jakob Krebs, Daniel Amir, Mark Silberstein

This paper proposes MoX, an optimized load-oblivious routing method for efficient training and inference of sparse Model-of-Experts (MoE) on static direct-connect fabrics.

View →