AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Stabilizing Self-Consuming Diffusion Models with Latent Space Filtering

Zhongteng Cai, Yaxuan Wang, Yang Liu, Xueru Zhang

AAAI 2026 · Image generation › Autoregressive and latent generation · approach: Latent diffusion with learned tokenizers · 4 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
filter accumulated data by probing-classifier confidence instead of random sampling (ACUR)ACUR · MNISTFIDImproved
filter accumulated data by probing-classifier confidence instead of random sampling (ablation)ACUR · MNISTreal image ratio in filtered setImproved
filter by batch-level OLE score instead of random sampling (ablation)ACUR · MNISTself-consuming stabilityNo clear effect
add 30% fresh real data per generation (SYN-ADD) to pure synthetic trainingSYN · MNIST and CelebAFID, precision, recallImproved
accumulate historical data (ACU) instead of pure synthetic loopSYN · MNIST and CelebAFID, precision, recallImproved
add score-function extrapolation (SIMS) across generationsACUR · MNIST and CelebAFID, precision, recallHurt
add self-correction toward real cluster centers (SC)ACUR · MNIST and CelebArecall and FIDHurt
replace full accumulation with LSF on fixed budget (storage)ACU-LSF · CelebAtraining data storage: 582 MB -> 109 MBImproved

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