AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

E²LoRA: Efficient and Effective Low-Rank Adaptation with Entropy-Guided Adaptive Sharing

Minglei Li, Peng Ye, Jingqi Ye, haonan he, Tao Chen

ICLR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: LoRA variants and theory

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 entropy-guided sharing and rank allocation to LoRALoRA · GSM8Kaccuracy: 70.21 -> 70.51 (6.82M -> 3.66M params)Improved
add E2LoRA to LoRALoRA · HumanEvalPass@1: 42.68 -> 44.31Improved
add E2LoRA to ShareLoRAShareLoRA · HumanEvalPass@1: 43.69 -> 44.71Improved
add E2LoRA to ShareLoRAShareLoRA · GSM8Kaccuracy: 70.51 -> 70.26No clear effect
add E2LoRA to LoRALoRA · GLUE (RoBERTa-Base)average score: 85.87 -> 85.57 (0.3M -> 0.16M params)No clear effect
add E2LoRA to ShareLoRAShareLoRA · GLUE (RoBERTa-Base)average score: 84.99 -> 85.40Improved
add E2LoRA to LoRALoRA · CLIP image classification (7 datasets)average accuracy: 89.08 -> 89.81 (1.31M -> 0.66M params)Improved
add E2LoRA to ShareLoRAShareLoRA · CLIP image classification (7 datasets)average accuracy: 88.75 -> 89.73 (0.72M -> 0.39M params)Improved
add heterogeneity-based rank allocation (HRA) on top of LSS (ablation)E2LoRA · GSM8K (Llama-3.1-8B)accuracy: 69.45 -> 70.51Improved
add local similarity-based sharing (LSS) on top of HRA (ablation)E2LoRA · GSM8K (Llama-3.1-8B)accuracy: 71.19 -> 70.51 (6.82M -> 3.61M params)Mixed
use proxy entropy similarity instead of cosine similarity (ablation)E2LoRA · GSM8K (Llama-3.1-8B)accuracy: 66.67 -> 70.51Improved
use proxy entropy similarity instead of KL similarity (ablation)E2LoRA · GSM8K (Llama-3.1-8B)accuracy: 67.57 -> 70.51Improved

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