AI Paper Atlas

Research map / Continual learning / Continual fine-tuning of LLMs

Energy-Structured Low-Rank Adaptation for Continual Learning

Longhua Li, Lei Qi, Qi Tian, Xin Geng

ICML 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation · 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
add classifier alignment (ablation)E2-LoRA · Cars-196Last-Acc: 63.34 -> 75.82Improved
add self-distillation (ablation)E2-LoRA · Cars-196Last-Acc: 72.15 -> 75.82Improved
add self-distillation without classifier alignment (ablation)E2-LoRA · ImageNet-RLast-Acc: 80.28 -> 80.28No clear effect
add classifier alignment (ablation)E2-LoRA · ImageNet-RLast-Acc: 80.28 -> 82.52Improved
use E2-LoRA instead of O-LoRA with KD and CA (ablation)LoRA CL backbone · ImageNet-RLast-Acc: 77.92 -> 82.77Improved
use E2-LoRA instead of InfLoRA with KD and CA (ablation)LoRA CL backbone · Cars-196Last-Acc: 69.73 -> 75.82Improved
dynamic rank allocation instead of full rank (ablation)E2-LoRA · ImageNet-R (50 tasks)Last-Acc: 68.52 -> 78.58Improved
dynamic rank allocation instead of fixed rank dout/50 (ablation)E2-LoRA · ImageNet-R (10 tasks)Last-Acc: 77.71 -> 82.77Improved
dynamic rank allocation instead of fixed rank dout/5 (ablation)E2-LoRA · ImageNet-R (10 tasks)Last-Acc: 82.01 -> 82.77Improved
add PCA energy-structured transformation (ablation)E2-LoRA · ImageNet-RLast-Acc: 78.93 -> 82.77Improved
add PCA energy-structured transformation (ablation)E2-LoRA · CIFAR-100Last-Acc: 87.04 -> 92.13Improved
increase proxy samples beyond 16 (ablation)E2-LoRA · ImageNet-R and CIFAR-100Last-AccNo clear effect

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