AI Paper Atlas

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

LongT2IBench: A Benchmark for Evaluating Long Text-to-Image Generation with Graph-structured Annotations

Zhichao Yang, Tianjiao Gu, Jianjie Wang, Feiyu Lin, Xiangfei Sheng, Pengfei Chen, Leida Li

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
add Hierarchical Alignment CoT (ablation)LongT2IExpert · LongT2IBench scoringAvg. (SRCC+PLCC)/2: 0.516 -> 0.557Improved
add Hierarchical Alignment CoT (ablation)LongT2IExpert · LongT2IBench interpretingOverall accuracy: 39.9% -> 53.2%Improved
add interpretation task in multi-task training (ablation)LongT2IExpert · LongT2IBench scoringAvg. (SRCC+PLCC)/2: 0.474 -> 0.557Improved
add scoring task in multi-task training (ablation)LongT2IExpert · LongT2IBench interpretingOverall accuracy: 32.8% -> 53.2%Improved
fine-tune baselines on LongT2IBench training dataPickScore · LongT2IBench scoring (overall)Avg. (SRCC+PLCC)/2: 0.336 -> 0.438Improved
fine-tune baselines on LongT2IBench training dataImageReward · LongT2IBench scoring (overall)Avg. (SRCC+PLCC)/2: 0.227 -> 0.439Improved
fine-tune baselines on LongT2IBench training dataFGA-BLIP2 · LongT2IBench scoring (overall)Avg. (SRCC+PLCC)/2: 0.246 -> 0.425Improved
increase prompt length to 110+ wordsVLM-based evaluators (CLIP-style encoders) · LongT2IBench scoring, 110+ wordsSRCC: ImageReward 0.283 -> -0.023 (30-50 to 110+ words)Hurt
use MLLM-based evaluator instead of VLM-based at 110+ wordsQ-Eval-Score · LongT2IBench scoring, 110+ wordsSRCC: Q-Eval-Score 0.422 vs HPSv2 0.148Improved
longer prompts lower LongT2IExpert correlationLongT2IExpert · LongT2IBench scoringSRCC: 0.781 (30-50 words) -> 0.431 (110+ words)Hurt

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