AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation

Sucheng Ren, Qihang Yu, Ju He, Xiaohui Shen, Alan Yuille, Liang-Chieh Chen

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Next-scale and token autoregressive images · 65 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
predict 8x8 cells instead of individual tokens (ablation)xAR-B · ImageNet-256 (400 epochs)FID: 3.51 -> 2.48Improved
predict cells instead of coarse-to-fine scales (ablation)xAR-B · ImageNet-256 (400 epochs)FID: 2.90 -> 2.48Improved
predict cells instead of the entire image (ablation)xAR-B · ImageNet-256 (400 epochs)FID: 3.13 -> 2.48Improved
increase cell size from 1x1 to 8x8 (ablation)xAR-B · ImageNet-256 (400 epochs)FID: 3.51 -> 2.48Improved
increase cell size beyond 8x8 to 16x16 (ablation)xAR-B · ImageNet-256 (400 epochs)FID: 2.48 -> 3.13Hurt
add Noisy Context Learning instead of clean-context teacher forcing (ablation)xAR-B · ImageNet-256 (400 epochs)FID: 3.45 -> 2.48Improved
sample noise time steps randomly rather than with increasing or decreasing order (ablation)xAR-B Noisy Context Learning · ImageNet-256 (400 epochs)FID: 2.78 -> 2.48 (decreasing vs random)Improved
use rectangular cells instead of square cells (ablation)xAR · ImageNet-256FIDNo clear effect
use xAR-B with each entity type versus prior method of same entity type (ablation)xAR-B vs LlamaGen-L, PAR-L, DiT-L/2, VAR-d16 · ImageNet-256 (400 epochs)FID: 3.80 -> 3.51 (token), 5.02 -> 3.13 (image), 3.30 -> 2.90 (scale)Improved
use xAR-L instead of REPAImageNet-256 sampling · ImageNet-256 throughputimages per second: 0.6 -> 3.2Improved

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