AI Paper Atlas

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

Semantic Browsing: Controllable Diversity for Image Generation

Sara Dorfman, Maya Vishnevsky, Omer Dahary, Or Patashnik, Danny Cohen-Or

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 0 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
induce structured semantic diversity via agentic JSON-prompt tree instead of stochastic VLM seedingFIBO · MS-COCO 50 promptsVendi score: 2.60 -> 3.34Improved
same changeFIBO · MS-COCO 50 promptsDINO similarity: 0.76 -> 0.61Improved
same changeFIBO · MS-COCO 50 promptsVQAScore: 0.93 -> 0.90Hurt
same change vs CADSFIBO · MS-COCO 50 promptsAesthetic score: 6.30 -> 6.52Improved
add Context Analyst agent (ablation)Semantic Browsing · Hierarchical Consistencyconsistency: 0.82 -> 0.87Improved
add Context Analyst agent (ablation)Semantic Browsing · MS-COCOVQAScore: 0.90 -> 0.90No clear effect
add Critic agent (ablation)Semantic Browsing · MS-COCOVQAScore: 0.87 -> 0.90Improved
add Critic agent (ablation)Semantic Browsing · Hierarchical Consistencyconsistency: 0.87 -> 0.87No clear effect
separate Brainstormer and Decision Maker roles (ablation)Semantic Browsing · tree DINO distance (mean)DINO distance: 0.362 -> 0.389Improved
swap Gemini 2.5 Flash VLM for ChatGPT-5.5 (ablation)Semantic Browsing · MS-COCOVendi score: 3.34 -> 3.30No clear effect
increase tree depth (BF=1) from gallery 5 to 20 (ablation)Semantic Browsing · scaling ablationVQAScore: 0.81 -> 0.75Hurt
increase branching factor (D=1) from 5 to 20 (ablation)Semantic Browsing · scaling ablationVendi score: 2.05 -> 3.13Improved

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