AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

LoFA: Learning to Predict Personalized Prior for Fast Adaptation of Visual Generative Models

Yiming Hao, Mutian Xu, Chongjie Ye, Jie Qin, Shunlin Lu, Yipeng Qin, Xiaoguang Han

CVPR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: LoRA variants and theory

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 Stage-I LoRA response map prediction (ablation)LoFA · Human action video (text)FVD: 665.4 -> 589.8Improved
add Stage-I LoRA response map prediction (ablation)LoFA · Identity image generationFace Sim: 0.497 -> 0.548Improved
add Stage-I LoRA response map prediction (ablation)LoFA · Text-to-video stylizationCSD-Score: 0.394 -> 0.427Improved
supervise Stage-I with response maps rather than a lightweight LoRA hypernetwork (ablation)LoFA · Human action video (text)FVD: 655.1 -> 589.8Improved
take base model weights as input with prompt via cross-attention instead of prompt as input (ablation)LoFA · Human action video (text)FVD: 653.7 -> 589.8Improved
use 2% response threshold instead of 1% (ablation)LoFA · Human action video (text)FVD: 634.7 -> 589.8Improved
use 2% response threshold instead of 3% (ablation)LoFA · Human action video (text)FVD: 622.5 -> 589.8Improved
inject Stage-I feature at 4th and 8th blocks (ablation)LoFA · Human action video (text)FVD: 660.1 -> 589.8Improved
attend Stage-I feature at more early layers (2 to 8) (ablation)LoFA · Human action video (text)FVD: 660.1 -> 680.9Hurt
increase training LoRA pairsLoFA · Human action video (text)qualityImproved
predict LoRA directly vs per-case LoRA trainingLoFA · Human action video (text)FVD: 609.5 -> 589.8Improved

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