AI Paper Atlas

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

AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generation

Xinyu Hou, Xiaoming Li, Chen Change Loy

IJCV 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 3 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 anchor loss (no mapping network) (ablation)rTI · Race biasD_KL: 0.8230 -> 0.3461Improved
add anchor loss (no mapping network) (ablation)rTI · Gender biasD_KL: 0.3124 -> 0.3121No clear effect
add adaptive mapping network on top of anchor loss (ablation)anchor-loss-only · Gender biasD_KL: 0.3121 -> 0.1290Improved
add adaptive mapping network on top of anchor loss (ablation)anchor-loss-only · Race biasD_KL: 0.3461 -> 0.3488No clear effect
use Transformer instead of MLP mapping network (ablation)AITTI · Gender biasD_KL: 0.4059 -> 0.1290Improved
place mapping module before text transformer instead of after (ablation)AITTI · Gender biasD_KL: 0.3388 -> 0.1290Improved
use 1 inclusive token instead of 2 (ablation)AITTI · Gender biasD_KL: 0.2074 -> 0.1290Improved
use 10 instead of 5 training samples per combination (ablation)AITTI · Gender biasD_KL: 0.1988 -> 0.1290Improved
use 10 instead of 20 training samples per combination (ablation)AITTI · Gender biasD_KL: 0.1573 -> 0.1290Mixed
train on SD1.5 synthetic images instead of online images (ablation)AITTI · Gender biasD_KL: 0.2386 -> 0.1520Improved
use 4 transformer blocks instead of 2 (ablation)adaptive mapping network · Gender biasD_KL: 0.1630 -> 0.1290Mixed
combine gender, race and age inclusive tokensAITTI · Multi-biasD_KL: 0.2319 -> 0.2790Mixed

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