AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Breaking the Scale Barrier: One-Shot Knowledge Transfer via Frequency Transform

Jianlu Shen, Fu Feng, Yucheng Xie, Jiaqi Lv, Xin Geng

ICML 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Parameter-efficient transfer analysis · 0 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 MLP weight transfer (vs none) (ablation)FRONT · DeiT-Ti L12 to L4, ImageNet-1Ktop-1 accuracy (%): 34.7 -> 54.8Improved
transfer all modules instead of MLP only (ablation)FRONT · DeiT-Ti L12 to L4, ImageNet-1Ktop-1 accuracy (%): 54.8 -> 55.3Improved
transfer W_qkv and W_o in addition to nothing (attention only) (ablation)FRONT · DeiT-Ti L12 to L4, ImageNet-1Ktop-1 accuracy (%): 34.7 -> 50.1Improved
add self-attention weight transfer (W_qkv, W_o) (ablation)FRONT · BERT-B to BERT-S, GLUEaverage score: 53.31 -> 63.61Improved
add MLP weight transfer only (ablation)FRONT · BERT-B to BERT-S, GLUEaverage score: 53.31 -> 58.08Improved
transfer all modules instead of attention only (ablation)FRONT · BERT-B to BERT-S, GLUEaverage score: 63.61 -> 64.63Improved
add W_qkv only transfer (ablation)FRONT · BERT-B to BERT-S, CoLAMCC: 8.14 -> 4.63Hurt
add frequency-regularized refinement (FRONT+)FRONT · DeiT-Ti 12 layers, ImageNet-1K 10 epochstop-1 accuracy (%): 65.3 -> 67.5Improved
add refinement with gamma=1/4 at r=0.67 (ablation)FRONT · DeiT-Ti L8, ImageNet-1Ktop-1 accuracy (%): 64.79 -> 68.02Improved
increase frequency ratio r from 0.33 to 1.00 without refinement (ablation)FRONT · DeiT-Ti L8, ImageNet-1Ktop-1 accuracy (%): 60.63 -> 66.19Improved
increase decay gamma from 1/4 to 1 (ablation)FRONT+ · DeiT-Ti L8, ImageNet-1K, r=0.67top-1 accuracy (%): 68.02 -> 66.60Hurt
use extreme regularization lambda (1e-5 or 5e-3) (ablation)FRONT++ · DeiT-Ti-L10 targettop-1 accuracyHurt

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