TTE-Flash: Accelerating Reasoning-based Multimodal Representations via Think-Then-Embed Tokens

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheng, Jianpeng, Wu, Xian, Zhang, Jiangfan, Bao, Wentao, Ahuja, Chaitanya, Mishra, Shlok Kumar, Yu, Hanchao, Gao, Yang, Xia, Fan, Guo, Qi, Zhai, Shaodan, Fan, Xiangjun, Xiao, Jun
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.16638