AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment

Riccardo Zaccone, Stefanos Laskaridis, Marco Ciccone, Samuel Horváth

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
train nested submodels (NSL) instead of only the full model (PTS) (ablation)low-rank elastic model · linear-model theory and MNIST toysubmodel optimality gap: gap zero only for NSLImproved
train all submodels jointly (ASL) instead of nested (ablation)low-rank elastic model · linear-model theory and MNIST toysubmodel optimality gap: strictly positive gapHurt
add distillation-based submodel training on top of DataSVD + DP selection (ablation)FlexRank · GPT-2 eval losslossImproved
train each layer independently during distillation instead of end-to-end (ablation)FlexRank · GPT-2 eval losslossHurt
increase DataSVD calibration samples above 128 (ablation)FlexRank initialization · GPT-2 eval losslossNo clear effect
train a single submodel at one budget instead of nested sampling (ablation)FlexRank · GPT-2 eval losslossHurt
use nested weight-shared submodels instead of independent submodels at equal total budget (ablation)FlexRank · Llama-3.2-1Baverage accuracy: slightImproved
replace ACIP LoRA adapters with nested distillation of shared weightsACIP · Llama models commonsense averageaverage accuracyImproved
use DP rank selection over uniform truncationFlexRank · GPT-2compression profileImproved

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