arXiv Machine Learning
Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 20
Toward a mechanistic understanding of inference in visual cortex and diffusion models
arXiv:2607. 15693v1 Announce Type: cross Abstract: We describe a model of perceptual inference in primary visual cortex (V1) equivalent to a minimal diffusion model whose function can be readily understood from its parameters.
arXiv AI
Oct 15
SharedSAE: a unified sparse dictionary across u-net blocks and denoising time for diffusion models
arXiv:2610.13997v1 Announce Type: cross Abstract: Concept representations in diffusion models drift across network depth and denoising time, yet existing sparse autoencoders offer only per-block or p...
arXiv Computer Vision
Sep 15
Diffusion Trajectory Modeling for Semantic Correspondence
Diffusion Trajectory Modeling (DTM) treats the evolving feature maps of diffusion models as temporally structured trajectories rather than static snapshots. By interpreting each spatial patch’s progression across multiple timesteps as a trajectory, DTM captures semantic correspondence cues that prior methods miss. Experiments on SPair-71k, SPair-U, and AP-10K demonstrate that DTM achieves strong performance, highlighting the semantic value embedded in the diffusion process’s temporal axis.
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
Sep 30
On Trajectory-Aware Training for Masked Diffusion Language Models
arXiv:2609.37974v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The m...
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.