2 papers
cs.LG2026
FarSkip-Collective: Unhobbling Blocking Communication in Mixture of Experts Models
Yonatan Dukler, Guihong Li, Deval Shah +3
Blocking communication presents a major hurdle in running MoEs efficiently in distributed settings. To address this, we present FarSkip-Collective which modifies the architecture o…
cs.CV2026
BlindSight: Harnessing Sparsity for Efficient Vision-Language Models
Tharun Adithya Srikrishnan, Deval Shah, Timothy Hein +3
Large vision-language models (VLMs) enable joint processing of text and images. However, incorporating vision data significantly increases the prompt length, resulting in a longer…