arXiv AI
SharedSAE: a unified sparse dictionary across u-net blocks and denoising time for diffusion models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Oct 8
Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models
arXiv:2605.27813v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models generate images by iterative denoising, so their internal layers produce trajectories of activations rather th...
arXiv Machine Learning
Jun 19
On the Redundancy of Timestep Embeddings in Diffusion Models
arXiv:2606. 20416v1 Announce Type: new Abstract: Diffusion models rely heavily on explicit timestep embeddings to modulate the denoising process across various noise scales.
arXiv AI
Jul 1
Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models
arXiv:2606. 31699v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated features can serve as controllable intervention points.
arXiv AI
Jun 16
DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing
arXiv:2606. 15796v1 Announce Type: cross Abstract: Mechanistic interpretability seeks to explain neural network behavior by decomposing model computations into interpretable features and circuits.
Hugging Face Trending Papers
Jun 22
PeLAP-A: Adaptive Latent Pruning for Lightweight Latent Diffusion Models
Latent diffusion models achieve strong generative performance by operating in a compressed latent space produced by a variational autoencoder (VAE). However, it remains unclear whether all latent channels contribute equally to the diffusion process, or whether significant redundancy exists.
arXiv Machine Learning
Aug 4
A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs
arXiv:2603. 07475v4 Announce Type: replace-cross Abstract: Autoregressive (AR) language models build representations incrementally via left-to-right prediction, while diffusion language models (dLLMs) are trained through full-sequence denoising.