Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Kibum, Kim, Jiwan, Min, Kyle, Wang, Yueqi, Moon, Jinyoung, McAuley, Julian, Park, Chanyoung
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.20937