arXiv:2605. 27482v2 Announce Type: replace-cross Abstract: While orthogonal subspace methods try to mitigate task interference in Continual Learning (CL), they often suffer from energy diffusion across the basis, hindering knowledge compaction and exhausting capacity for future tasks.
By Longhua Li, Lei Qi, Qi Tian, Xin Geng
The paper introduces LoDA, a LoRA-based continual learning method that decomposes update spaces into task‑shared and truly task‑specific subspaces using energy‑based objectives. By fixing down‑projections and learning up‑projections with Gradient‑Aligned Optimization, LoDA recalibrates general updates in closed form after each task, aiming to improve knowledge sharing and isolation. Experiments show that LoDA outperforms existing CL methods.
By Lingfeng He, De Cheng, Huaijie Wang, Xi Yang, Nannan Wang, Xinbo Gao
arXiv:2608.27518v1 Announce Type: new
Abstract: Continual learning (CL) and model merging (MM) both aim to obtain a single model that performs well across multiple tasks, challenged respectively by c...
By Shangge Liu, Yuehan Yin, Yinghuan Shi, Lei Wang, Wenbin Li
arXiv:2602. 00722v2 Announce Type: replace Abstract: Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge.
By Hao Gu, Mao-Lin Luo, Zi-Hao Zhou, Han-Chen Zhang, Min-Ling Zhang, Tong Wei
The paper introduces LoRA‑Norm, a post‑training normalization technique for Low‑Rank Adaptation (LoRA) that rebalances the gains of learned singular directions without altering the directions themselves. LoRA‑Norm uses spectral rebalancing and nuclear‑norm restoration to preserve total spectral mass, requiring no calibration data or extra training and adding no inference overhead. Experiments on two backbones and three adaptation tasks show that LoRA‑Norm improves both specialization and capability retention, outperforming other post‑hoc spectral pruning and gradient‑guided editing methods.
By Zailong Tian, Yanzhe Chen, Zhuoheng Han, Houfeng Wang, Lizi Liao
arXiv:2608. 12332v1 Announce Type: cross Abstract: In recent years, low-rank adaptation (LoRA) has emerged as a significant paradigm that freezes pre-trained weights and introduces small, learnable adapters instead of fine-tuning the full set of parameters.
By Hyowon Wi, Noseong Park