AI Paper Atlas

Research map / Image generation / Editing and style transfer

VMDiff: Visual Mixing Diffusion for Limitless Cross-Object Synthesis

Zeren Xiong, Yue Yu, Ze-dong Zhang, Shuo Chen, Jian Yang, Jun Li

ICLR 2026 · Image generation › Editing and style transfer · approach: Inversion-based diffusion editing · 2 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 blending-noise refinement (BNoise) before mixing denoise (ablation)VMDiff · IIOFsimilarity score SS: 1.570 -> 1.586Improved
add alpha search (golden section) over mixing ratio (ablation)VMDiff · IIOFsimilarity score SS: 1.586 -> 2.025Improved
add beta1/beta2 search (ablation)VMDiff · IIOFsimilarity score SS: 2.025 -> 2.068Improved
interpolate embeddings instead of concatenating them in BNoise (ablation)VMDiff · IIOFsimilarity score SS: 1.586 -> 1.551 (before), 1.532 (after)Hurt
use VMDiff vs best multi-concept baseline MIP-AdapterMIP-Adapter · IIOFsimilarity score SS: 1.866 -> 2.068Improved
VMDiff versus MIP-Adapter on LLaVA coherenceMIP-Adapter · IIOFVQAScore-LLaVA single-entity coherence: 0.417 vs 0.413Hurt
human preference for VMDiff over baselinesGPT-4o / DreamO etc. · user studyvote share (%): 12.9 -> 67.3Improved
VMDiff iterative optimization costVMDiff · runtime per pairtime: 2 min 46 sec vs 8 sec (DreamO)Hurt

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