paper-with-me

Papers

Pruned Adaptation Modules: A Simple yet Strong Baseline for Continual Foundation Models

2026-03-22 · Elif Ceren Gok Yildirim, Murat Onur Yildirim, Joaquin Vanschoren arxiv

The continual learning literature has rapidly shifted from traditional class incremental learning (CIL) techniques to foundation model (FM)-based CIL methods without a clear understanding of how these newer approaches compare to strong, lightweight convolutional baselines. This abrupt transition has created a substantial methodological gap, making it difficult to assess whether recent FM-based CIL progress reflects genuine advances or merely the absence of rigorous baselines. To address this gap, we introduce Pruned Adaptation Modules (PAM), a simple yet effective method that freezes the vast majority of the pre-trained ResNet while enabling scalable continual adaptation through sparse task-specific layers. PAM yields up to a ~5x reduction in trainable parameters and a ~6x reduction in total parameters, significantly reducing the cost of continual updates. Across diverse benchmarks, PAM consistently mitigates catastrophic forgetting and outperforms state-of-the-art FM-based CIL approaches. Our findings position PAM as a strong and transparent baseline that helps bridge the gap between traditional and FM-based CIL, guiding future research for a more accurate assessment of true progress in continual adaptation. The code can be found at: https://github.com/ElifCerenGokYildirim/PAM.

📄 PDF Abstract BibTeX arXiv:2603.21170

Code (0)

등록된 구현이 없습니다.

Tasks

Class Incremental LearningContinual Learning

Similar Papers 제목 키워드 기반

Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation

2021-03-25 · NAACL 2021 4 · Shuhao Gu, Yang Feng, Wanying Xie

Domain Adaptation is widely used in practical applications of neural machine translation, which aims to achieve good performance on both the general-domain and in-domain. However, the existing methods for domain adaptati…

Domain AdaptationKnowledge DistillationMachine TranslationTranslation

ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models

2024-03-24 · Zequan Liu, Jiawen Lyn, Wei Zhu, Xing Tian 외

Parameter-efficient fine-tuning (PEFT) is widely studied for its effectiveness and efficiency in the era of large language models. Low-rank adaptation (LoRA) has demonstrated commendable performance as a popular and repr…

parameter-efficient fine-tuning

A Simple but Strong Baseline for Sounding Video Generation: Effective Adaptation of Audio and Video Diffusion Models for Joint Generation

2024-09-26 · Masato Ishii, Akio Hayakawa, Takashi Shibuya, Yuki Mitsufuji

In this work, we build a simple but strong baseline for sounding video generation. Given base diffusion models for audio and video, we integrate them with additional modules into a single model and train it to make the m…

Inductive BiasVideo Generation

Three-Stage Learning Unlocks Strong Performance in Simple Models for Long-Term Time Series Forecasting

2026-05-13 · Zhenan Yu, Guangxin Jiang, Jin Yang arxiv

Recent studies on long-term time series forecasting have shown that simple linear models and MLP-based predictors can achieve strong performance without increasingly complex architectures. However, many competitive basel…

Time Series Forecasting

RoRA: Efficient Fine-Tuning of LLM with Reliability Optimization for Rank Adaptation

2025-01-08 · Jun Liu, Zhenglun Kong, Peiyan Dong, Changdi Yang 외

Fine-tuning helps large language models (LLM) recover degraded information and enhance task performance. Although Low-Rank Adaptation (LoRA) is widely used and effective for fine-tuning, we have observed that its scaling…