arXiv (All)
open access
Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models
Text-to-image diffusion models generate images by iterative denoising, so their internal layers produce trajectories of activations rather than single static representations. Sparse autoencoders (SAEs) have recently been used to decompose diffusion activations into interpretable features, but most a
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising#819321
- V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising#809328
- Exploring Text Classification Models with Sparse Autoencoders#1035110
- EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders#985267
- Rethinking Memorization Mitigation in Diffusion Models: Reinforcing Text Conditioning#1156994
Record · ID 1232748
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive