AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation

Yang Chen, Xiaowei Xu, Shuai Wang, Xinwen Zhang, Qiushi Guo, Tiezheng Ge, Limin Wang

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 1 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
add masking (ratio 0.4-0.6) to encoder input (ablation)MIMFlow · ImageNet 256x256 (50 ep.)gFID: 29.0 -> 12.82Improved
add masking (ratio 0.4-0.6) to encoder input (ablation)MIMFlow · ImageNet linear probingtop-1 accuracy: 56.6 -> 71.3Improved
use mixed mask/no-mask strategy or low mask ratios (ablation)MIMFlow · ImageNet 256x256 (50 ep.)gFID: 12.82 -> 26.98 (mix); 24.47 (0.2-0.4)Hurt
add masking bottleneck in progressive ablation (ablation)MIMFlow · ImageNet 256x256 (no CFG)gFID: 18.71 -> 10.14Improved
add DINO+CLIP auxiliary supervision (ablation)MIMFlow · ImageNet 256x256 (no CFG)gFID: 19.52 -> 18.71No clear effect
use learnable tokens while removing GAN loss (ablation)MIMFlow baseline · ImageNet 256x256 (no CFG)gFID: 11.24 -> 19.52Hurt
add GAN fine-tuning of decoder (ablation)MIMFlow · ImageNet 256x256 (no CFG)gFID: 10.14 -> 6.15Improved
add HOG as auxiliary target (ablation)MIMFlow · ImageNet 256x256gFID: 12.46 -> 20.77 (CLIP+HOG)Hurt
combine DINO and CLIP auxiliary targets instead of DINO only (ablation)MIMFlow · ImageNet 256x256gFID: 12.89 -> 12.46Improved
increase latent tokens from 128 to 192 (ablation)MIMFlow · ImageNet 256x256gFID: 12.46 -> 30.42Hurt
use latent noise sigma 0.5 instead of 0.3 (ablation)MIMFlow · ImageNet 256x256gFID: 12.82 -> 17.69Hurt
use latent noise sigma 0.2 instead of 0.3 (ablation)MIMFlow · ImageNet 256x256gFID: 12.82 -> 14.30Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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