Motivation. Large language models (LLMs) have exhibited remarkable proficiency in diverse
software engineering (SE) tasks, such as code summarization, code translation, and code …

Humans have the ability to constantly learn new knowledge. However, for artificial
intelligence, trying to continuously learn new knowledge usually results in catastrophic …

Recently, transfer learning has gained popularity in the machine learning community.
Transfer Learning (TL) has emerged as a promising paradigm that leverages knowledge …

In continual learning, previously learnt knowledge tends to be overlapped by the
subsequent training tasks. This bottleneck, known as catastrophic forgetting, has recently …

Catastrophic forgetting refers to a neural network's detrimental loss of previously learned
information upon acquiring new knowledge. Recent continual learning methodologies grant …

In continual learning, previous learned knowledge tends to be overlapped by the
subsequent training tasks. This bottleneck, known as catastrophic forgetting (CF), has …

Catastrophic forgetting is a problem that occurs when an artificial neural network in the
continual learning setting replaces historic information as additional information is acquired …