AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

PEFTDiff: Diffusion-Guided Transferability Estimation for Parameter-Efficient Fine-Tuning

Prafful Kumar Khoba, Zijian Wang, Chetan Arora, Mahsa Baktashmotlagh

ICCV 2025 · Architectures and efficiency › Pruning and efficient tuning · approach: Adapter-based parameter-efficient tuning · 2 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
combine intra-class compactness and inter-class separability scores (ablation)PEFTDiff · VTAB-1kweighted Kendall tau_w: 0.174 / 0.22 -> 0.517Improved
use diffusion step t=10 instead of t=5 or t=20 (ablation)PEFTDiff · VTAB-1kweighted Kendall tau_w: 0.439 / 0.107 -> 0.517Improved
use kNN graph with k=20 (ablation)PEFTDiff · VTAB-1kweighted Kendall tau_wImproved
use diffusion-based score instead of LogME for PEFT rankingPEFT selection · VTAB-1kweighted Kendall tau_w: 0.306 -> 0.517Improved
use diffusion-based score on structured VTAB tasksPEFTDiff · VTAB-1k Structuredweighted Kendall tau_w: 0.397 vs LogME 0.391Mixed
use diffusion-based score on FGVC instead of best baselinePEFT selection · FGVC (5 datasets)weighted Kendall tau_w: 0.311 -> 0.462Improved
use diffusion score instead of exhaustive PEFT fine-tuning for selectionPEFT selection · VTAB-1kcomputation time (min): 11074.5 -> 55.44Improved

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