AK
Ashutosh Kumar
On Valency
published · living versionsW_j5854z57·v1 · currentpublished
Sonar-MoE: In-Backward Expert Updates for Memory-Efficient Mixture-of-Experts Training
with Avni Mittal, Avinash Anand, Dikshant Kukreja, Kritarth Prasad +5
1 version
Preprints & journals
We couldn't confidently link this author to their published research yet.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.