M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lei, Hongyang, Cheng, Xiaolong, Qin, Qi, Wang, Dan, Fan, Kun, Huang, Huazhen, Gu, Qingqing, Wu, Yetao, Jiang, Zhonglin, Chen, Yong, Ji, Luo
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2409.05929