To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …

As a special case of machine learning, incremental learning can acquire useful knowledge
from incoming data continuously while it does not need to access the original data. It is …

For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing
the human level, with AI agents considered a promising vehicle for this pursuit. AI agents are …

Test-time adaptation provides an effective means of tackling the potential distribution shift
between model training and inference, by dynamically updating the model at test time. This …

Thanks to the large pre-trained vision-language models (VLMs) like CLIP, we can craft a
zero-shot classifier by discrete prompt design, eg, the confidence score of an image …

The landscape of publicly available vision foundation models (VFMs) such as CLIP and
SAM is expanding rapidly. VFMs are endowed with distinct capabilities stemming from their …

Deep network architectures struggle to continually learn new tasks without forgetting the
previous tasks. A recent trend indicates that dynamic architectures based on an expansion …

State-of-the-art deep neural networks are still struggling to address the catastrophic
forgetting problem in continual learning. In this paper, we propose one simple paradigm …

This paper proposed a new online continual learning approach called OCM based on
mutual information (MI) maximization. It achieves two objectives that are critical in dealing …

While deep learning and deep reinforcement learning (RL) systems have demonstrated
impressive results in domains such as image classification, game playing, and robotic …