AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Unleashing the Potential of Large Language Models for Text-to-Image Generation Through Autoregressive Representation Alignment

Xing Xie, Jiawei Liu, Ziyue Lin, Huijie Fan, Zhi Han, Yandong Tang, Liangqiong Qu

AAAI 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 4 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
align to interleaved <HYBNEXT> token instead of fixed <REP> token (ablation)ARRA (Chameleon 7B) · MIMIC-CXRFID: 6.26 -> 5.30Improved
align to interleaved <HYBNEXT> token instead of fixed <REP> token (ablation)ARRA-Adapt (Lumina-mGPT 7B) · MIMIC-CXRFID: 4.85 -> 4.15Improved
add global visual alignment loss (ablation)ARRA (Chameleon 7B) · MIMIC-CXRFID: 7.11 -> 5.30Improved
add global visual alignment loss (ablation)ARRA-Adapt (Lumina-mGPT 7B) · MIMIC-CXRFID: 5.10 -> 4.15Improved
use CLS token aggregation instead of average pooling (ablation)ARRA (Chameleon 7B) · MIMIC-CXRFID: 6.56 -> 5.30Improved
use CLS token alone instead of concatenating CLS and average pooling (ablation)ARRA (Chameleon 7B) · MIMIC-CXRFID: 5.93 -> 5.30Improved
use BioMedCLIP instead of Med-SAM as alignment target (ablation)ARRA (Chameleon 7B) · MIMIC-CXRFID: 6.54 -> 5.30Improved
use Med-SAM instead of BioMedCLIP as alignment target (ablation)ARRA-Adapt (Lumina-mGPT 7B) · MIMIC-CXRFID: 4.15 -> 4.08Mixed
use general CLIP-L instead of BioMedCLIP as alignment target (ablation)ARRA-Adapt (Lumina-mGPT 7B) · MIMIC-CXRFID: 4.15 -> 4.63Hurt
add ARRA alignment to LlamaGen trained from scratchLlamaGen · ImageNetFID: 4.33 -> 3.61 (343M)Improved
add ARRA alignment to LlamaGen trained from scratchLlamaGen 343M · ImageNetIS: 286.6 -> 262.6Hurt
add ARRA alignment to LlamaGen trained from scratchLlamaGen · LAION-COCO 2.4M subsetFID: 12.78 -> 11.67 (343M); 11.88 -> 10.45 (3.1B)Improved

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