相关论文: More Than Catastrophic Forgetting: Integrating Gen…

Deep neural networks for scene perception in automated vehicles achieve excellent results for the domains they were trained on. However, in real-world conditions, the domain of operation and its underlying data distribution are subject to…

Continual learning (CL) in large language models (LLMs) is an evolving domain that focuses on developing efficient and sustainable training strategies to adapt models to emerging knowledge and achieve robustness in dynamic environments. Our…

A catastrophic forgetting problem makes deep neural networks forget the previously learned information, when learning data collected in new environments, such as by different sensors or in different light conditions. This paper presents a…

The ability to continuously process and retain new information like we do naturally as humans is a feat that is highly sought after when training neural networks. Unfortunately, the traditional optimization algorithms often require large…

The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting. Previous work has shown that leveraging memory in the form of a replay buffer can reduce performance…

Catastrophic forgetting is a pervasive issue for pre-trained language models (PLMs) during continual learning, where models lose previously acquired knowledge when sequentially trained on a series of tasks. The model's ability to retain old…

The substantial interest in updating Large Language Models (LLMs) without retraining from scratch is accompanied by several challenges. This is particularly true when updating LLMs with datasets that necessitate domain-expert reasoning…

Foundations models are presented as generalists that often perform well over a myriad of tasks. Fine-tuning these models, even on limited data, provides an additional boost in task-specific performance but often at the cost of their wider…

Domain Incremental Learning (DIL) is a continual learning sub-branch that aims to address never-ending arrivals of new domains without catastrophic forgetting problems. Despite the advent of parameter-efficient fine-tuning (PEFT)…

Fundamental physics often confronts complex symbolic problems with few guiding exemplars or established principles. While artificial intelligence (AI) offers promise, its typical need for vast datasets to learn from hinders its use in these…

Large Language Models (LLMs) excel in diverse tasks but often underperform in specialized fields due to limited domain-specific or proprietary corpus. Continual pre-training (CPT) enhances LLM capabilities by imbuing new domain-specific or…

The goal of Few-Shot Continual Learning (FSCL) is to incrementally learn novel tasks with limited labeled samples and preserve previous capabilities simultaneously, while current FSCL methods are all for the class-incremental purpose.…

A growing number of state-of-the-art transfer learning methods employ language models pretrained on large generic corpora. In this paper we present a conceptually simple and effective transfer learning approach that addresses the problem of…

Large Language Models (LLMs) have achieved exceptional capabilities in open generation across various domains, yet they encounter difficulties with tasks that require intensive knowledge. To address these challenges, methods for integrating…

Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task. Many recent methods focus on…

Efficient continual learning techniques have been a topic of significant research over the last few years. A fundamental problem with such learning is severe degradation of performance on previously learned tasks, known also as catastrophic…

Catastrophic forgetting remains a formidable obstacle to building an omniscient model in large language models (LLMs). Despite the pioneering research on task-level forgetting in LLM fine-tuning, there is scant focus on forgetting during…

The rapid integration of large language models (LLMs) into everyday workflows has transformed how individuals perform cognitive tasks such as writing, programming, analysis, and multilingual communication. While prior research has focused…

Aligned Large Language Models (LLMs) showcase remarkable versatility, capable of handling diverse real-world tasks. Meanwhile, aligned LLMs are also expected to exhibit speciality, excelling in specific applications. However, fine-tuning…

In the literature, many continual learning (CL) algorithms have been proposed to address the issue of catastrophic forgetting in ML models (i.e., learning new tasks leads to the loss of performance on previously learned tasks). Although all…