arXiv cs.AI· Longhao Lei, Lan Yao·· 3 天前AI 评分27
SharedSAE：跨 U-Net 模块与去噪时间的扩散模型统一稀疏字典
SharedSAE: a unified sparse dictionary across u-net blocks and denoising time for diffusion models
AI 导读
SharedSAE 为 SDXL 1.0 学习了一个跨四个 U-Net 注意力模块和全部 50 个去噪步共享的稀疏字典，通过块特定低秩输入适配器与时间条件模块吸收时间非平稳性。基于该字典的局部特征抑制将 I2P 检测器阳性子集中 NudeNet 阳性生成数从 139 降至 1。追踪稀疏特征还发现，概念表示在生成过程中从最早的降采样模块向中间及更晚模块重新分布。
正文 · 原文
Abstract:Concept representations in diffusion models drift across network depth and denoising time, yet existing sparse autoencoders offer only per-block or per-timestep dictionaries, leaving no single feature dictionary for localization and intervention in the network. We present Shared Sparse Autoencoder (SharedSAE), which learns one sparse dictionary shared across four U-Net attention blocks and all 50 denoising steps of SDXL 1.0. A block-specific low-rank input adapter aligns the residual distribution of each block before the shared encoder, and a temporal conditioning module with a shared timestep branch and a block-timestep correction branch absorbs temporal non-stationarity. Despite spanning both axes, Shared SAE preserves a coherent dictionary structure. Built on the shared dictionary, localized feature suppression reduces the number of NudeNet-positive generations in the I2P detector-positive subset from 139 to 1. Tracing sparse features across the trajectory further reveals that concept representations are redistributed across U-Net blocks during generation, shifting from the earliest downsampling block toward intermediate and later blocks as denoising proceeds. SharedSAE thus provides a unified, interpretable, and intervention-ready representation space for diffusion models, enabling concept analysis and erasure at any covered block and denoising step.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.13997 [cs.CV] |
| (or arXiv:2610.13997v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13997 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lan Yao [view email]
[v1]
Sun, 27 Sep 2026 00:35:51 UTC (33,502 KB)
来源：arXiv cs.AI · arxiv.org