RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Byeongchan, Sehanobish, Arijit, Dubey, Avinava, Oh, Min-hwan, Choromanski, Krzysztof
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/2605.10706