AI Paper Atlas

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

Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models

Zengbin Wang, Xuecai Hu, Yong Wang, Feng Xiong, Man Zhang, Xiangxiang Chu

ICLR 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 21 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
fine-tune on SpatialT2ISD-XL · SpatialGenEval (Qwen2.5-VL-72B judge)overall accuracy: 41.2 -> 45.4Improved
fine-tune on SpatialT2IUniWorld-V1 · SpatialGenEval (Qwen2.5-VL-72B judge)overall accuracy: 54.2 -> 59.9Improved
fine-tune on SpatialT2IOmniGen2 · SpatialGenEval (Qwen2.5-VL-72B judge)overall accuracy: 56.4 -> 60.8Improved
fine-tune on SpatialT2IUniWorld-V1 · SpatialGenEval (Qwen2.5-VL-72B judge) (Comparison)accuracy: 26.1 -> 34.6Improved
fine-tune on SpatialT2IUniWorld-V1 · SpatialGenEval (Qwen2.5-VL-72B judge) (Motion)accuracy: 69.6 -> 66.0Hurt
fine-tune on SpatialT2IOmniGen2 · SpatialGenEval (Qwen2.5-VL-72B judge) (Object)accuracy: 51.5 -> 61.8Improved
use higher-scoring source model subsets for SFT data (Unipic-v2 54.3, Bagel 57.0, Qwen-Image 60.6) (ablation)SD-XL and OmniGen2 · SpatialGenEval (Qwen2.5-VL-72B judge)overall accuracyImproved
scale SFT data from 0% to 100% by adding better subsets (ablation)OmniGen2 · SpatialGenEval (Qwen2.5-VL-72B judge)overall accuracyImproved
use T5 text encoder (SD-3) instead of CLIP only (SD-1.5)SD-3 / SD-1.5 · SpatialGenEval (Qwen2.5-VL-72B judge)overall accuracy: 28.5 -> 54.6Improved
scale diffusion model from 8B SD-3.5-L to 20B Qwen-ImageQwen-Image · SpatialGenEval (Qwen2.5-VL-72B judge)overall accuracy: 54.0 -> 60.6Improved
use GPT-4o instead of Qwen2.5-VL-72B as judgeSpatialGenEval · SpatialGenEval top-5 modelsmodel ranking: 60.8 vs 60.6No clear effect

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