AI Paper Atlas

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

MoCL: Metabolic Optimization for Curvature-Aware Continual Learning

Jiajun Lai, Qi Liu, Shijie Li, Huaiguang Jiang

ICML 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation

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 soft metabolic gating instead of binary hard projection (ablation)MoCL · ImageNet-R (N=20)A_last: 77.68 -> 79.22Improved
use soft metabolic gating instead of binary hard projection (ablation)MoCL · ImageNet-R (N=20)A_avg: 84.11 -> 85.03Improved
use Tsallis entropy gate instead of Shannon entropy (ablation)MoCL · ImageNet-R (N=20)A_last: 78.43 -> 79.22Improved
use Tsallis entropy gate instead of Shannon entropy (ablation)MoCL · ImageNet-R (N=20)A_avg: 84.57 -> 85.03Improved
use Tsallis gate instead of sigmoid gating (ablation)MoCL · ImageNet-R (N=20)A_last: 74.88 -> 79.22Improved
use Tsallis gate instead of sigmoid gating (ablation)MoCL · ImageNet-R (N=20)A_avg: 82.54 -> 85.03Improved
use K-FAC activation and gradient subspaces instead of gradient subspace only (ablation)MoCL · ImageNet-R (N=20)A_last: 76.85 -> 79.22Improved
use K-FAC activation and gradient subspaces instead of activation subspace only (ablation)MoCL · ImageNet-R (N=20)A_last: 75.90 -> 79.22Improved
use K-FAC activation and gradient subspaces instead of gradient subspace only (ablation)MoCL · ImageNet-R (N=20)A_avg: 83.74 -> 85.03Improved
use K-FAC activation and gradient subspaces instead of activation subspace only (ablation)MoCL · ImageNet-R (N=20)A_avg: 82.56 -> 85.03Improved
replace CoSO with MoCL as the method (more tasks)MoCL · ImageNet-R (N=5 to N=20)A_last: 82.29 vs 81.53 (N=5); 79.22 vs 77.57 (N=20)Improved
replace CoSO with MoCLMoCL · ImageNet-A (N=10)A_avg: 68.36 vs 71.27Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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