AI Paper Atlas

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

Mod-Adapter: Tuning-Free and Versatile Multi-concept Personalization via Modulation Adapter

Weizhi Zhong, Huan Yang, Zheng Liu, Huiguo He, Zijian He, Xuesong Niu, Di ZHANG, Guanbin Li

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Multi-concept composition · 13 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 VLM-guided pre-training (ablation)Mod-Adapter · DreamBench-Abs (multi-concept)CP·PF: 0.17 -> 0.62Improved
add VLM-guided pre-training (ablation)Mod-Adapter · DreamBench-Abs (single-concept)CP·PF: 0.24 -> 0.54Improved
add Mixture-of-Experts layer (ablation)Mod-Adapter · DreamBench-Abs (multi-concept)CP·PF: 0.35 -> 0.62Improved
add Mixture-of-Experts layer (ablation)Mod-Adapter · DreamBench-Abs (single-concept)CP·PF: 0.42 -> 0.54Improved
add VL cross-attention (ablation)Mod-Adapter · DreamBench-Abs (multi-concept)CP·PF: 0.39 -> 0.62Improved
add VL cross-attention (ablation)Mod-Adapter · DreamBench-Abs (single-concept)CP·PF: 0.49 -> 0.54Improved
add VL cross-attention (ablation)Mod-Adapter · DreamBench-Abs (multi-concept)CLIP-T: 0.329 -> 0.330No clear effect
use k-means routing instead of learnable linear gating (ablation)Mod-Adapter · DreamBench-Abs (multi-concept)CP·PF: 0.49 -> 0.62Improved
use k-means routing instead of learnable linear gating (ablation)Mod-Adapter · DreamBench-Abs (single-concept)CP·PF: 0.44 -> 0.54Improved
increase number of experts from 1 to 12 (ablation)Mod-Adapter · DreamBench-Abs (multi-concept)CP·PF: 0.22 -> 0.62Improved
increase number of experts from 4 to 12 (ablation)Mod-Adapter · DreamBench-Abs (single-concept)CP·PF: 0.31 -> 0.54Improved
use hierarchical instead of k-means clustering (ablation)Mod-Adapter · DreamBench-Abs (multi-concept)CP·PF: 0.62 -> 0.63No clear effect

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