AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

CART: Compositional AutoRegressive Transformer for Image Generation

Siddharth Roheda, Rohit Chowdhury, Aniruddha Bala, Rohan Jaiswal

AAAI 2026 · Image generation › Autoregressive and latent generation · approach: Next-scale and token autoregressive images · 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 base-detail token decomposition (next-detail) replacing next-scaleVAR-d30 · ImageNet 256x256FID: 1.70 -> 1.57Improved
add base-detail token decomposition at small scaleVAR-d16 · ImageNet 256x256FID: 3.30 -> 2.89Improved
use multi-scale tokenization for base factor (ablation)CART-d16 · ImageNet 256x256FID: 2.90 -> 2.89No clear effect
increase decomposition order from 0 to 3 (ablation)CART-d30 · ImageNet 256x256FID: 1.70 -> 1.57Improved
increase decomposition order from 3 to 4 (ablation)CART-d30 · ImageNet 256x256FID: 1.57 -> 1.60Hurt
add rejection samplingCART-d30 · ImageNet 256x256FID: 1.65 -> 1.57Improved
train at 256 and generate 512 with patchwise detail prediction (overlapping)CART-256 · ImageNet 512x512FID: 2.63 (VAR-d36-s trained at 512) -> 2.54Improved
use non-overlapping instead of 50% overlapping patches (ablation)CART-256 · ImageNet 512x512FID: 2.54 -> 2.85Hurt
use CART for super-resolution vs ResShiftCART-512-d30 · ImageNet SR 128->512PSNR: PSNR 24.65 vs 24.90; CLIPIQA 0.672 vs 0.603Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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