AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Learning to Learn Weight Generation via Local Consistency Diffusion

Yunchuan Guan, Yu Liu, Ke Zhou, Zhiqi Shen, Jenq-Neng Hwang, Lei Li

CVPR 2026 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space · 8 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 meta-learning (bi-level optimization) to diffusion weight generation (ablation)OCD · Mini-ImageNet 5-way 1-shotaccuracy (%): 59.76 -> 62.53Improved
add meta-learning to diffusion weight generation (ablation)OCD · Omniglot 5-way 1-shotaccuracy (%): 95.04 -> 96.65Improved
add local target weights without consistency loss (ablation)Mv-Di · Mini-ImageNet 5-way 1-shotaccuracy (%): 62.53 -> 49.72Hurt
add local target weights without consistency loss (ablation)Mv-Di · Omniglot 5-way 1-shotaccuracy (%): 96.65 -> 94.28Hurt
add local consistency loss (ablation)Tw-Di · Mini-ImageNet 5-way 1-shotaccuracy (%): 49.72 -> 64.87Improved
add local consistency diffusion (ablation)Mv-Di · Omniglot 5-way 1-shotaccuracy (%): 96.65 -> 97.34Improved
add SAM and data augmentation in weight preparation (ablation)Mc-Di · Omniglot 5-way 1-shotaccuracyImproved
use Mc-Di for transfer learning vs D2NWGMc-Di · CIFAR-10accuracy (%): 60.42 -> 63.57Improved
use Mc-Di vs D2NWGMc-Di · CIFAR-100accuracy (%): 51.50 -> 50.69Hurt
use Mc-Di vs Meta-BaselineMc-Di · Omniglot 5-way 1-shotaccuracy (%): 97.75 -> 97.34Hurt
use Mc-Di vs D2NWGMc-Di · Tiered-ImageNet 5-way 5-shotaccuracy (%): 85.05 -> 88.58Improved
use Mc-Di vs OCD on DomainNetMc-Di · DomainNet 5-way 1-shotaccuracy (%): 64.58 -> 69.05Improved

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