AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

ProReGen: Progressive Residual Generation under Attribute Correlations

Ruby Shrestha, Ajay Gopi, Casey Meisenzahl, Bipin Lekhak, Linwei Wang

ICLR 2026 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 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
train g_mjr then g_res in two stages instead of simultaneously (ablation)ProReGen-GAN · Colored-MNIST (95% correlation)minority correctness: 0.3557 -> 0.9256Improved
two-stage training instead of single-stage (ablation)ProReGen-GAN · Colored-MNIST (95% correlation)minority FID: 65.0227 -> 17.2562Improved
two-stage training instead of single-stage (ablation)ProReGen-GAN · Colored-MNIST (95% correlation)majority correctness: 0.9289 -> 0.9592No clear effect
perturb x1 to simulate error in m(x1) (80% of samples) (ablation)ProReGen-GAN · Colored-MNIST (95% correlation)overall correctness: 0.9256 -> 0.8589Hurt
use one conv block instead of two in the residual sub-network (ablation)ProReGen-GAN · Colored-MNIST (95% correlation)minority correctness: 0.9256 -> 0.6476Hurt
invert causal direction from digit->color to color->digit (ablation)ProReGen-GAN · Colored-MNISTminority correctness: 0.9396 -> 0.0811Hurt
add pseudo-supervision (causal-cHVAE) to c-VAEc-VAE · Colored-MNISTminority vs majority correctnessMixed
re-weight (upsample) minority samplesc-VAE, c-GAN, c-DM · Colored-MNISTcorrectness and coverageMixed
add ProReGen to naive c-GAN/c-DMc-GAN, c-DM · Corrupted-CIFAR10minority correctnessImproved
add pseudo-supervision (causal-GAN) to c-GANc-GAN · MNIST-Correlationminority correctnessNo clear effect

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