AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Energy Guided Diffusion for Generating Neurally Exciting Images

Paweł A. Pierzchlewicz, Konstantin Friedrich Willeke, Arne Nix, Pavithra Elumalai, Kelli Restivo, Tori Shinn, Cate Nealley, Gabrielle Rodriguez, Saumil Patel, Katrin Franke, Andreas S. Tolias, Fabian H. Sinz

NeurIPS 2023 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use EGG diffusion instead of gradient ascent to generate MEIsV4 encoding models · MEI cross architecture (Gaussian)mean unit activation: 5.51 -> 6.53Improved
use EGG diffusion instead of gradient ascent to generate MEIsV4 encoding models · MEI cross architecture (Attention)mean unit activation: 4.42 -> 5.50Improved
use EGG diffusion instead of gradient ascent to generate MEIsAttention V4 model · MEI within architecture (Attention)mean unit activation: 7.59 -> 10.56Improved
use EGG diffusion instead of gradient ascent to generate MEIsGaussian V4 model · MEI within architecture (Gaussian)mean unit activation: 11.43 -> 11.76No clear effect
diffusion guidance instead of 1000-step gradient ascentMEI generation · MEI generation timegeneration time (s): 219s -> 46sImproved
use Attention readout instead of Gaussian readout (task-driven core) (ablation)V4 encoding model · Macaque V4 neural predictioncorrelation to average: 0.262 -> 0.276Improved
use Attention readout instead of Gaussian readout (data-driven core) (ablation)V4 encoding model · Macaque V4 neural predictioncorrelation to average: 0.229 -> 0.294Improved
use data-driven core instead of task-driven core (Attention readout) (ablation)V4 encoding model · Macaque V4 neural predictioncorrelation to average: 0.276 -> 0.294Improved
use data-driven core instead of task-driven core (Gaussian readout) (ablation)V4 encoding model · Macaque V4 neural predictioncorrelation to average: 0.262 -> 0.229Hurt
use EGG diffusion instead of gradient descent for image reconstructionGaussian model reconstruction · Reconstruction, cross architectureimages with lower L2 distance (%): 98%Improved
AdamW instead of SGD for gradient ascent baseline (ablation)GA MEIs · MEI generationrelative activation: r = 0.69Hurt
100 instead of 1000 gradient ascent steps (ablation)GA MEIs · MEI generationrelative activation: r = 0.95Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy