AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

FlexLoRA: Entropy-Guided Flexible Low-Rank Adaptation

Muqing Liu, Chongjie Si, Yuheng Jia

ICLR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: LoRA variants and theory · 3 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
use entropy importance instead of nuclear norm (ablation)FlexLoRA · GLUE devAvg. score: 87.7 -> 89.1Improved
use entropy importance instead of Frobenius norm (ablation)FlexLoRA · GLUE devAvg. score: 87.1 -> 89.1Improved
add rank expansion to prune-only (ablation)FlexLoRA · GLUE devAvg. score: 87.5 -> 89.1Improved
add rank pruning to expand-only (ablation)FlexLoRA · GLUE devAvg. score: 87.6 -> 89.1Improved
use zero-impact init instead of small-init (ablation)FlexLoRA · GLUE devAvg. score: 87.8 -> 89.1Improved
use zero-impact init instead of zero-init (ablation)FlexLoRA · GLUE devAvg. score: 87.1 -> 89.1Improved
use zero-impact init instead of orthogonal-init (ablation)FlexLoRA · GLUE devAvg. score: 88.0 -> 89.1Improved
FlexLoRA instead of AdaLoRADeBERTaV3-base · GLUE devAvg. score: 88.1 -> 89.1Improved
FlexLoRA instead of AdaLoRA at rank 8LLaMA3-8B · Commonsense reasoningAvg. accuracy: 85.1 -> 85.2No clear effect
raise rank from 8 to 32 for FlexLoRA (ablation)LLaMA3-8B · Commonsense reasoningAvg. accuracy: 85.2 -> 85.5Improved
FlexLoRA instead of LoRA r=32LLaMA3-8B · Commonsense reasoningAvg. accuracy: 85.4 -> 85.5No clear effect
FlexLoRA instead of LoRA r=14ViT-B/16 · VTAB-1KAvg. accuracy: 66.7 -> 67.8Improved

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