Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Du, Junhao, Xue, Jialong, Li, Anqi, Dai, Jincheng, Lu, Guo
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.21957