AI Paper Atlas

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

DGS: Dual Gradient and Semantic-Shift Guided Low-Rank Adaptation for Class Incremental Learning

Kai Li, Jiafeng Li, Lianghua He, Ying Wen

CVPR 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Synthetic data and merging for CLIP

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 Dual Gradient update (fuse raw and projected gradients) (ablation)task-specific LoRA baseline · ImageNet-R B0Inc20A_last: 78.90 -> 79.68Improved
add Dual Gradient update (ablation)task-specific LoRA baseline · ImageNet-R B0Inc20forgetting F_last: 9.86 -> 6.88Improved
add Dual Gradient update (ablation)task-specific LoRA baseline · ObjectNet B0Inc10A_last: 61.30 -> 62.64Improved
add patch-level alignment loss on top of DG (ablation)DGS · ImageNet-R B0Inc20A_last: 79.68 -> 80.15Improved
add patch-level alignment loss on top of DG (ablation)DGS · ImageNet-R B0Inc20forgetting F_last: 6.88 -> 5.30Improved
add classifier alignment with semantic shift on top of DG (ablation)DGS · ImageNet-R B0Inc20A_last: 79.68 -> 81.26Improved
add classifier alignment on top of DG without patch alignment (ablation)DGS · ImageNet-R B0Inc20forgetting F_last: 6.88 -> 8.25Hurt
add classifier alignment on top of DG without patch alignment (ablation)DGS · ObjectNet B0Inc10forgetting F_last: 10.08 -> 14.57Hurt
combine DG, patch alignment and classifier alignment (ablation)DGS · ImageNet-R B0Inc20A_last: 78.90 -> 81.72Improved
combine DG, patch alignment and classifier alignment (ablation)DGS · ObjectNet B0Inc10A_last: 61.30 -> 64.85Improved
increase interpolation weight alpha toward projected gradient (ablation)Dual Gradient · ImageNet-R and ObjectNetaccuracy / forgettingMixed
vary tau scale factor from 10 to 20 to 40 (ablation)DGS · ImageNet-R B0Inc20A_last: 79.15 -> 81.72 -> 79.68Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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