AI Paper Atlas

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

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens

Dongwon Kim, Ju He, Qihang Yu, Chenglin Yang, Xiaohui Shen, Suha Kwak, Liang-Chieh Chen

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 42 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 improved one-stage training recipe (ablation)TiTok VQ 64 tokens · ImageNetrFID: 5.15 -> 2.43Improved
add text-aware de-tokenization (ablation)TiTok VQ 32 tokens · ImageNet val zero-shotrFID: 7.72 -> 3.95Improved
add text-aware de-tokenization (ablation)TiTok VQ 128 tokens · ImageNet val zero-shotrFID: 2.63 -> 1.53Improved
add text-aware de-tokenization (ablation)TiTok KL 128 tokens · ImageNet val zero-shotrFID: 1.02 -> 0.90Improved
use continuous KL tokens instead of VQ (ablation)TiTok 32 tokens · ImageNet val zero-shotrFID: 7.72 -> 2.56Improved
add text-aware tokenizer TA-TiTok (ablation)MaskGen-L KL · MJHQ-30KFID: 9.82 -> 8.13Improved
add aesthetic score conditioning (ablation)MaskGen-L KL with TA-TiTok · MJHQ-30KFID: 8.13 -> 7.24Improved
add aesthetic score conditioning (ablation)MaskGen-L KL with TiTok · GenEvalOverall: 0.47 -> 0.49Improved
add text guidance to encoder as well as decoder (ablation)TA-TiTok KL 32 tokens · ImageNet val zero-shotrFID: 1.53 -> 1.65No clear effect
use CLIP embeddings instead of token IDs for text guidance (ablation)TA-TiTok KL 32 tokens · ImageNet val zero-shotrFID: 1.62 -> 1.53Improved
increase token count from 32 to 128 (ablation)MaskGen-L VQ · MJHQ-30KFID: 9.11 -> 7.74Improved
increase token count from 32 to 128 (ablation)MaskGen-L VQ · GenEvalOverall: 0.43 -> 0.53Improved

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