AI Paper Atlas

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

DOS: Directional Object Separation in Text Embeddings for Multi-Object Image Generation

Dongnam Byun, Jungwon Park, Jungmin Ko, Changin Choi, Wonjong Rhee

AAAI 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 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 DOS vectors to CLIP text embeddingsSDXL · Similar Shapessuccess rate: 48.00% -> 64.00%Improved
add DOS vectors to CLIP text embeddingsSDXL · Many Objectssuccess rate: 23.00% -> 48.00%Improved
add DOS vectors to CLIP text embeddingsSDXL · Dissimilar Background Biasesmixture rate: 22.50% -> 17.00%Improved
add DOS vectors to CLIP text embeddingsSD3.5 · Many Objectssuccess rate: 70.00% -> 76.50%Improved
use DOS instead of TEBOptSDXL · four multi-object benchmarkssuccess rate: 10.50%-24.00% higher SRImproved
use DOS instead of latent modification (A&E, CONFORM)SDXL · Similar Shapesinference time: 58.83 s -> 13.87 s (A&E)Improved
apply DOS to object-noun token embeddings only (ablation)DOS SDXL · Similar Shapessuccess rate: 48.0% -> 58.0%Improved
apply DOS to EOT/pooled embeddings only (ablation)DOS SDXL · Dissimilar Background Biasesmixture rate: 22.5% -> 17.5%Improved
apply DOS to all three embedding types vs one (ablation)DOS SDXL · Many Objectssuccess rate: 36.5% -> 48.0%Improved
use adaptive strengths instead of fixed 0.5 (ablation)DOS SDXL · Many Objectssuccess rate: 41.0% -> 48.0%Improved
use fixed strength 0.5 for separation vectors (ablation)DOS SDXL · Similar Shapessuccess rate: 48.0% -> 60.5%Improved
add DOS vectorsSDXL · Human preference, Similar Shapesvote share: 50.52% vs 13.62% (A&E)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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