AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis

Peng Zheng, Junke Wang, Yi Chang, Yizhou Yu, Rui Ma, Zuxuan Wu

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Next-scale and token autoregressive images · 3 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
condition MAR on discrete tokens (ablation)MAR · ImageNet 256x256gFID: reduces gFID by up to 0.2 points, IS up about 10 pointsImproved
add discrete token conditioning to MAR-H (fewer AR steps) (ablation)MAR-H · ImageNet 256x256sec/img: 1.678 -> 0.316Improved
use a stronger discrete AR model (RAR-XXL vs RAR-B) to produce conditions (ablation)DisCon-L · ImageNet 256x256gFID: 1.87 -> 1.38Improved
condition on weaker discrete AR models (RAR-B, RAR-L) (ablation)DisCon · ImageNet 256x256gFID: 1.74 -> 1.74 (RAR-L with DisCon-B)No clear effect
reduce AR steps from 256 to 64 in MAR vs DisCon at 16 steps (ablation)MAR vs DisCon · ImageNet 256x256gFIDImproved
apply CFG to continuous token generation (ablation)DisCon · ImageNet 256x256gFIDHurt

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