SharedSAE: a unified sparse dictionary across u-net blocks and denoising time for diffusion models

arXiv:2610.13997 · cs.CV, cs.AI, cs.LG · Submitted 2026-09-27 · Read on arXiv

cs.CV, cs.AI, cs.LG

Submitted: 2026-09-27

Updated: 2026-09-27

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Diffusion Model — 1× in this paper · explained in 10 episodes
• Diffusion Models — 1× in this paper · explained in 9 episodes

Sources

• SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders
• PEAK: Precise and Persistent Concept Erasure via k-Sparse Autoencoders
• Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models