AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

AdaRank: Adaptive Rank Pruning for Enhanced Model Merging

Chanhyuk Lee, Jiho Choi, Chanryeol Lee, Donggyun Kim, Seunghoon Hong

ICLR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Low-rank compression and merging · 12 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 AdaRank to Task ArithmeticTask Arithmetic · ViT-B/32, 8 tasksaverage accuracy: 69.2 -> 87.9Improved
add AdaRank to Iso-CTSIso-CTS · ViT-B/32, 8 tasksaverage accuracy: 84.9 -> 89.4Improved
add AdaRank to TSV-MTSV-M · ViT-B/32, 20 tasksaverage accuracy: 76.7 -> 86.9Improved
add AdaRank instead of AdaMerging to Task ArithmeticTA+AdaMerging · ViT-B/32, 8 tasksaverage accuracy: 80.1 -> 87.9Improved
add AdaRank instead of AdaMerging to Iso-CTSIso-CTS+AdaMerging · ViT-L/14, 8 tasksaverage accuracy: 95.4 -> 95.5Improved
add AdaRank to Task ArithmeticTask Arithmetic · GLUE 7 tasks, RoBERTa-baseaverage performance: 0.6718 -> 0.7032Improved
add AdaRank to CARTCART · GLUE 7 tasks, GPT-2average performance: 0.6182 -> 0.6587Improved
extend AdaRank mask from top-16% range to full range (ablation)AdaRank on TA · ViT-B/32, 8 tasksaverage accuracy: 87.5 -> 87.9Improved
restrict to top-16% fixed vs adaptive masking in top-16% range (ablation)Top-16% Fixed TA · ViT-B/32, 8 tasksaverage accuracy: 68.8 -> 87.5Improved
adapt mask B in addition to lambda (ablation)TA with lambda only · ViT-B/32, 8 tasksaverage accuracy: 80.1 -> 87.9Improved
adapt lambda in addition to mask B (ablation)CART with B only · ViT-B/32, 8 tasksaverage accuracy: 88.7 -> 89.2Improved
adapt only mask B instead of only lambda (ablation)CART · ViT-B/32, 8 tasksaverage accuracy: 85.9 -> 88.7Improved

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