相关论文: RegCL: Continual Adaptation of Segment Anything Mo…

Segment Anything Model (SAM) struggles in open-world scenarios with diverse domains. In such settings, naive fine-tuning with a well-designed learning module is inadequate and often causes catastrophic forgetting issue when learning…

Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acquisition in continual learning (CL). However, the requirement…

Continual Learning (CL) aims to enable models to continuously acquire new knowledge from a sequence of tasks with avoiding the forgetting of learned information. However, existing CL methods only rely on the parameters of the most recent…

Continual learning (CL) is essential for deploying large language models (LLMs) in dynamic real-world environments without the need for costly retraining. Recent model merging-based methods have attracted significant attention, but they…

Continual Learning (CL) strives to learn incrementally across tasks while mitigating catastrophic forgetting. A key challenge in CL is balancing stability (retaining prior knowledge) and plasticity (learning new tasks). While representative…

Recent advances in Multimodal Large Language Models (MLLMs) have enhanced their versatility as they integrate a growing number of modalities. Considering the heavy cost of training MLLMs, it is efficient to reuse the existing ones and…

Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors plasticity over the stability needed to retain prior knowledge. While existing approaches attempt to…

A common challenge in continual learning (CL) is catastrophic forgetting, where the performance on old tasks drops after new, additional tasks are learned. In this paper, we propose a novel framework called ReCL to slow down forgetting in…

Engineering problems that apply machine learning often involve computationally intensive methods but rely on limited datasets. As engineering data evolves with new designs and constraints, models must incorporate new knowledge over time.…

Continual learning (CL) aims to train models sequentially on multiple tasks while mitigating catastrophic forgetting of previously learned knowledge. Recent advances in large pre-trained models (LPMs) and model merging techniques, such as…

This paper introduces a continual learning approach named MagMax, which utilizes model merging to enable large pre-trained models to continuously learn from new data without forgetting previously acquired knowledge. Distinct from…

Model merging aims to integrate the strengths of multiple fine-tuned models into a unified model while preserving task-specific capabilities. Existing methods, represented by task arithmetic, are typically classified into global- and…

In Continual Learning (CL), a model is required to learn a stream of tasks sequentially without significant performance degradation on previously learned tasks. Current approaches fail for a long sequence of tasks from diverse domains and…

Model merging aims to combine multiple fine-tuned models into a single set of weights that performs well across all source tasks. While prior work has shown that merging can approximate the performance of individual fine-tuned models for…

Parameter-efficient continual learning has emerged as a promising approach for large language models (LLMs) to mitigate catastrophic forgetting while enabling adaptation to new tasks. Current Low-Rank Adaptation (LoRA) continual learning…

We unveil that internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge, and propose RECALL, a novel representation-aware model merging framework for continual learning without access to…

The success of large language models has garnered widespread attention for model merging techniques, especially training-free methods which combine model capabilities within the parameter space. However, two challenges remain: (1) uniform…

Existing work in continual learning (CL) focuses on mitigating catastrophic forgetting, i.e., model performance deterioration on past tasks when learning a new task. However, the training efficiency of a CL system is under-investigated,…

This paper investigates the linear merging of models in the context of continual learning (CL). Using controlled visual cues in computer vision experiments, we demonstrate that merging largely preserves or enhances shared knowledge, while…

Regression Mean (RegMean), an approach that formulates model merging as a linear regression problem, aims to find the optimal weights for each linear layer in the merged model by minimizing the discrepancy in predictions between the merged…