AI Paper Atlas

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

POCA: Pareto-Optimal Curriculum Alignment for Visual Text Generation

Yaohou Fan, Qingzhong Wang, Yongsong Huang, Junyi Liu, Tomo Miyazaki, Shinichiro Omachi

CVPR 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 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
replace weighted-sum rewards with Pareto-guided selection (ablation)GRPO baseline · AnyText-benchmark EnglishSen.ACC: 0.7246 -> 0.7378Improved
replace weighted-sum rewards with Pareto-guided selection (ablation)GRPO baseline · AnyText-benchmark ChineseSen.ACC: 0.6782 -> 0.6867Improved
use bi-directional instead of non-dominated-only Pareto sorting (ablation)Pareto-guided GRPO · AnyText-benchmark EnglishSen.ACC: 0.7227 -> 0.7378Improved
use bi-directional instead of fully-dominated-only sorting (ablation)Pareto-guided GRPO · AnyText-benchmark EnglishSen.ACC: 0.7274 -> 0.7378Improved
use bi-directional sorting in best@8 (ablation)Pareto-guided GRPO · AnyText-benchmark English best@8Sen.ACC: 0.8418 -> 0.8491Improved
add adaptive curriculum planning (10k prompts) (ablation)Pareto-guided GRPO · AnyText-benchmark EnglishSen.ACC: 0.7378 -> 0.7651Improved
increase curriculum data from 1k to 10k prompts (ablation)POCA · AnyText-benchmark EnglishSen.ACC: 0.7374 -> 0.7651Improved
use 1k-prompt curriculum instead of no curriculum (ablation)Pareto-guided GRPO · AnyText-benchmark EnglishSen.ACC: 0.7378 vs 0.7374No clear effect
use multi-stage curriculum instead of one stage (ablation)POCA · AnyText-benchmark EnglishSen.ACC: 0.7572 -> 0.7651Improved
add bi-directional Pareto sorting (ablation)Glyph-SDXL-v2 · AnyText-benchmark EnglishSen.ACC: 0.5950 -> 0.6119Improved
add curriculum on top of Pareto-guided (ablation)Glyph-SDXL-v2 · AnyText-benchmark EnglishSen.ACC: 0.6119 -> 0.6218Improved
add POCA to AnyTextAnyText · AnyText-benchmark EnglishSen.ACC: 0.7041 -> 0.7651Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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