MuLoRA introduces a spectrally balanced low‑rank adaptation method for continual learning, addressing the issue of spectral plasticity collapse where adaptation energy concentrates in few singular modes. It uses historical whitening to identify task‑adaptive input directions and approximate polar orthogonalization of momentum updates to reduce spectral concentration, ensuring effective utilization of the low‑rank space. Experiments on five class‑incremental benchmarks and eight incremental settings show MuLoRA achieving the highest mean accuracy in 15 of 16 metrics.
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.
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.
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...
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.
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.
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.
The paper introduces ISO-LoRA, an optimizer that improves rank utilization in Low‑Rank Adaptation (LoRA) by coupling factor updates through spectral descent on the induced tangent perturbation in weight space. Experiments on GPT‑2 adaptation show that standard optimizers like AdamW concentrate updates in a few singular directions, whereas ISO-LoRA distributes energy more evenly, leading to higher effective rank and better downstream performance across 0.1B‑7B models. The authors provide theoretical guarantees under a stylized spiked‑gradient model and demonstrate that ISO-LoRA consistently outperforms factor‑wise optimizers, especially at moderate‑to‑large LoRA ranks.
The paper investigates whether different parameter‑efficient fine‑tuning (PEFT) methods truly differ in their approach and impact. By comparing six methods on language and diffusion models, the authors find that many LoRA‑family techniques approximately preserve pretrained geometry, and that restoring slightly drifted singular‑value spectra largely maintains task performance, challenging the need for explicit geometric preservation. They also observe distinct adaptation–retention trade‑offs: LoRA limits forgetting best, DoRA scores higher on average, and PiSSA incurs more retention costs, with performance gains linked to modifications in specific spectral components.
arXiv:2602. 03846v2 Announce Type: replace-cross Abstract: We develop a continual learning method for pretrained models that \emph{requires no access to old-task data}, addressing a practical barrier in foundation model adaptation where pretraining distributions are often unavailable.
Geo-LoRA introduces a geometry‑aware framework for low‑rank adaptation in rehearsal‑free class‑incremental learning. It regulates the evolution of shared and task‑specific LoRA subspaces using Subspace Projection Preservation, Adaptive Core‑Slack Alignment, and Median‑Calibrated Block Overlap, ensuring smooth trajectories on the Grassmann manifold and balanced stability‑plasticity trade‑offs. The method achieves state‑of‑the‑art performance across multiple benchmarks without adding new adapter types.
arXiv:2607. 07719v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning adapts a large language model to one task cheaply, but across a task sequence LoRA-style methods keep stacking low-rank updates on the same frozen weight, so each new task tends to overwrite the previous ones.
The paper introduces FiUni, a Fisher-guided unified framework that performs batch-level task detection and parameter-efficient continual adaptation for large language models. By exploiting orthogonality in the Fisher information matrix’s Kronecker-Factored Approximate Curvature subspaces, FiUni constructs frozen subspaces to guide low-rank adaptation and matches incoming batch windows to historical subspaces. This approach allows the model to decide whether to reuse, expand, or create new subspaces, balancing knowledge sharing and task isolation while achieving competitive performance with fewer trainable parameters.