activity
20232026
most citedImproving vision-inspired keyword spotting using dynamic module skipping in streaming conformer encoder

4 citations · 5 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

Efficient Mixture-of-Experts with Speculative Decoding via Expert Coactivation

Kumari Nishu, Han-Byul Kim, Santosh Chilkunda +13

Mixture-of-Experts (MoE) models are increasingly deployed alongside Speculative Decoding (SD) to accelerate inference, but combining the two is challenging. SD improves the inferen…

cs.LG2025

MoE-PHDS: One MoE checkpoint for flexible runtime sparsity

Lauren. A Hannah, Soheil Zibakhsh, Kumari Nishu +4

Sparse Mixtures of Experts (MoEs) are typically trained to operate at a fixed sparsity level, e.g. in a top- gating function. This global sparsity level determines an operat…