paper-with-me

홈 › Papers

TailLoR: Protecting Principal Components in Parameter-Efficient Continual Learning

2026-06-04 · Marius Dragoi, Ioana Pintilie, Alexandra Dragomir, Antonio Barbalau, Florin Brad arxiv

Parameter-efficient finetuning methods based on spectral decomposition have enabled progress in Continual Learning. In this paper we introduce TailLoR, which utilizes the singular bases U and V of the pre-trained weights as a fixed reference frame to learn a low-rank update applied to the singular value matrix. A soft spectral penalty discourages updates aligned with dominant singular directions, reducing interference while routing fine-grained adaptation into the highly flexible, long-tail spectral coordinates.

📄 PDF Abstract BibTeX arXiv:2606.06494

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Continual Learning via Principal Components Projection

2019-09-25 · Gyuhak Kim, Bing Liu

Continual learning in neural networks (NN) often suffers from catastrophic forgetting. That is, when learning a sequence of tasks on an NN, the learning of a new task will cause weight changes that may destroy the learne…

Continual LearningLifelong learning

Least but not Last: Fine-tuning Intermediate Principal Components for Better Performance-Forgetting Trade-Offs

2026-02-03 · Alessio Quercia, Arya Bangun, Ira Assent, Hanno Scharr arxiv

Low-Rank Adaptation (LoRA) methods have emerged as crucial techniques for adapting large pre-trained models to downstream tasks under computational and memory constraints. However, they face a fundamental challenge in ba…

Continual Learning

Sparse principal component regression with adaptive loading

2014-02-26 · Shuichi. Kawano, Hironori Fujisawa, Toyoyuki Takada, Toshihiko Shiroishi

Principal component regression (PCR) is a two-stage procedure that selects some principal components and then constructs a regression model regarding them as new explanatory variables. Note that the principal components …

regression

Continual LLaVA: Continual Instruction Tuning in Large Vision-Language Models

2024-11-04 · Meng Cao, Yuyang Liu, Yingfei Liu, Tiancai Wang 외

Instruction tuning constitutes a prevalent technique for tailoring Large Vision Language Models (LVLMs) to meet individual task requirements. To date, most of the existing approaches are confined to single-task adaptatio…

ReCoLoRA: Spectrum-Aware Recursive Consolidation for Continual LLM Fine-Tuning

2026-07-04 · Wentao Lu arxiv

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 overwri…

parameter-efficient fine-tuning