AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles

Xiao Li, Yixuan Jia, Zekai Zhang, Xiang Li, Lianghe Shi, Jinxin Zhou, Zhihui Zhu, Liyue Shen, Qing Qu

ICML 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 0 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
extract diffusion features at an intermediate noise level instead of very low or very high noise (ablation)pretrained EDM (CIFAR10, CIFAR100) and SiT-XL/2 (ImageNet) · linear classification on diffusion featurestest accuracyImproved
train on full dataset longer (data-rich regime)EDM on CIFAR10 and SiT-B/2 on ImageNet-256 · FID and ICR over trainingICR and FIDImproved
continue training past the ICR minimum on limited dataEDM on 4096-image CIFAR10 subset · CIFAR10 limited datamemorization ratioHurt
continue training past the ICR minimum on limited dataEDM on 10K ImageNet-64 and SiT-B/2 on 20K ImageNet-256 · ImageNet limited dataICR and memorization ratioHurt
continue training on limited data (4096 images)EDM on CIFAR10 · trace of invariant covarianceTr(Sigma_s) and Tr(Sigma_xi)Mixed
continue training on full CIFAR10 (50K images)EDM on CIFAR10 · trace of invariant covarianceTr(Sigma_s) and Tr(Sigma_xi)Improved

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