AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks

Md Kowsher, Ali O. Polat, Ehsan Mohammady Ardehaly, Mehrdad Salehi, Zia Ghiasi, Prasanth Murali, Chen Chen

ICML 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Low-rank compression and merging · 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
increase slice rank from 1 to 5 (alternating row-column) (ablation)SliceFine · Math reasoning avg (LLaMA-3)average accuracy: 81.55 -> 82.13Improved
increase slice rank from 1 to 5 (row slices) (ablation)SliceFine · VTAB-1K image avgaverage accuracy: 88.15 -> 88.85Improved
increase slice rank beyond a moderate range (ablation)SliceFine · downstream accuracyvalidation accuracyHurt
choose slice position at different places in the weight matrix (ablation)SliceFine (rank 5) · Figure 3(b)accuracy: within ±1% of anchorNo clear effect
select slices by Wanda importance (most/least important, mixed, random) (ablation)SliceFine · Figure 3(c)accuracyNo clear effect
use slices from 'bad' LTH subnetworks instead of 'good' ones (ablation)SliceFine · Figure 3(d)accuracyNo clear effect
replace structured row/column slices with unstructured random masks (ablation)SliceFine · Tables 9 and 10accuracyNo clear effect
use unstructured random masks instead of structured slices (ablation)SliceFine · training efficiencymemory and training timeHurt
switch the active slice too frequently (ablation)SliceFine · switching interval ablationaccuracyHurt
use dynamic slice position instead of static (ablation)SliceFine · slice position ablationaccuracyImproved
prune a larger fraction of frozen backbone weights (ablation)SliceFine · backbone pruning (Figure 9)accuracyHurt
use SliceFine instead of LoRA/HRA/AdaLoRA for trainingPEFT on ViT/VideoMAE/RoBERTa · throughputiterations/s: 2.05 vs 1.78 (LoRA) and 1.62 (HRA)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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