We introduce a framework for online learning from a single continuous video stream-the way
people and animals learn without mini-batches data augmentation or shuffling. This poses …

In the field of electronic nose systems, sensor drift poses a significant challenge, affecting
the reliability and accuracy of gas detection. Current solutions often require labeled data and …

The prevalence of fake news on social media poses devastating and wide-ranging threats to
political beliefs, economic activities, and public health. Due to the continuous emergence of …

Abstract Continual Test-Time Adaptation (CTTA) involves adapting a pre-trained source
model to continually changing unsupervised target domains. In this paper, we systematically …

Lifelong person re-identification (LReID) suffers from the catastrophic forgetting problem
when learning from non-stationary data. Existing exemplar-based and knowledge distillation …

To accommodate real-world dynamics artificial intelligence systems need to cope with
sequentially arriving content in an online manner. Beyond regular Continual Learning (CL) …

A significant challenge in achieving ubiquitous Artificial Intelligence is the limited ability of
models to rapidly learn new information in real-world scenarios where data follows long …

Abstract Online Continual Learning (CL) solves the problem of learning the ever-emerging
new classification tasks from a continuous data stream. Unlike its offline counterpart in …

Online Continual Learning (OCL) aims at learning a model through a sequence of single-
pass data, usually encountering the challenges of catastrophic forgetting both between …

Recently, foundation language models (LMs) have marked significant achievements in the
domains of natural language processing (NLP) and computer vision (CV). Unlike traditional …