AI Paper Atlas

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

SIGMA: Selective-Interleaved Generation with Multi-Attribute Tokens

Xiaoyan Zhang, Zechen Bai, Haofan Wang, Yiren Song

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 1 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
post-train Bagel with SIGMA tokens on interleaved dataBagel · XVerse BenchCLIP-I: 66.32 -> 75.57Improved
post-train Bagel with SIGMABagel · SIGMA compositional benchmarkDINO: 41.62 -> 64.08Improved
SIGMA instead of XVerse on compositional generationXVerse · XVerse BenchCLIP: 33.94 -> 31.96Hurt
post-train Bagel with SIGMABagel · Selective generationCLIP-ES: 67.90 -> 58.02Improved
post-train Bagel with SIGMABagel · Layout onlyF1: 0.10 -> 0.44Improved
post-train Bagel with SIGMABagel · Layout onlyFID: 103.72 -> 121.08Hurt
post-train Bagel with SIGMABagel · Layout + referenceFID: 188.83 -> 108.05Improved
add attribute tokens, group mask and full finetuning (ablation)SIGMA · SIGMA compositional benchmarkCLIP-I: 62.67 -> 78.94Improved
full-parameter finetuning instead of LoRA (ablation)SIGMA · SIGMA compositional benchmarkCLIP-IImproved
add special attribute tokens (ablation)SIGMA · SIGMA compositional benchmarkCLIPImproved
add group-scoped attention mask (ablation)SIGMA · SIGMA compositional benchmarkCLIP-IImproved

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