AI Paper Atlas

Research map / Continual learning / Online and replay-based

Continual Personalization for Diffusion Models

Yu-Chien Liao, Jr-Jen Chen, Chi-Pin Huang, Ci-Siang Lin, Meng-Lin Wu, Yu-Chiang Frank Wang

ICCV 2025 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 3 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
select concept neurons instead of fine-tuning randomly picked neurons of equal number (ablation)CNS · Single-concept personalizationCLIP-T: 73.30 -> 76.95Improved
select concept neurons instead of random neurons (ablation)CNS · Multi-concept personalizationCLIP-T: 72.92 -> 79.22Improved
add neuron regularization loss L_reg (ablation)CNS · Single-concept personalizationCLIP-I: 73.06 -> 74.88Improved
add neuron regularization loss L_reg (ablation)CNS · Multi-concept personalizationCLIP-T: 77.02 -> 79.22Improved
fine-tune concept neurons incrementally instead of storing and fusing per-concept LoRAsCNS · Multi-concept personalization (fusion cost)fusion time (s): 727 -> 0 (vs Mix-of-Show)Improved
CNS vs Mix-of-Show on single-concept image alignmentCNS · Single-concept personalizationCLIP-I: 75.86 -> 74.88Hurt
exclude general neurons from base neurons when selecting concept neuronsCNS · neuron selectionneuron fraction updated: about 5% of cross-attention neurons, 0.13% of parametersImproved

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