In the rapidly evolving domain of machine learning, the ability to adapt to unforeseen
circumstances and novel data types is of paramount importance. The deployment of Artificial …

Existing research has shown that large language models (LLMs) exhibit remarkable
performance in language understanding and generation. However, when LLMs are …

Abstract Online Task-Free Continual Learning (OTFCL) aims to learn novel concepts from
streaming data without accessing task information. Most memory-based approaches used in …

Distillation strategies are currently the primary approaches for mitigating forgetting in class
incremental learning (CIL). Existing methods generally inherit previous knowledge from a …

Deep representation learning methods struggle with continual learning, suffering from both
catastrophic forgetting of useful units and loss of plasticity, often due to rigid and unuseful …

Deep neural networks have demonstrated susceptibility to adversarial attacks. Adversarial
defense techniques often focus on one-shot setting to maintain robustness against attack …

In this work, we investigate exemplar-free class incremental learning (CIL) with knowledge
distillation (KD) as a regularization strategy, aiming to prevent forgetting. KD-based methods …

Currently, most applications in the Industrial Internet of Things (IIoT) still rely on CNN-based
neural networks. Although Transformer-based large models (LMs), including language …

In this paper, we introduce a novel continual audio-visual sound separation task, aiming to
continuously separate sound sources for new classes while preserving performance on …

Remote photoplethysmography (rPPG) has gained significant attention in recent years for its
ability to extract physiological signals from facial videos. While existing rPPG measurement …