CASL: Concept-Aligned Sparse Latents for Interpreting Diffusion Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Zhenghao, Xiong, Guangzhi, Wang, Boyang, Sinha, Sanchit, Zhang, Aidong
Format:	Preprint
Published:	2026
Subjects:	Machine Learning 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/2601.15441