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 …

Biological organisms learn from interactions with their environment throughout their lifetime.
For artificial systems to successfully act and adapt in the real world, it is desirable to similarly …

Incrementally learning new information from a non-stationary stream of data, referred to as
'continual learning', is a key feature of natural intelligence, but a challenging problem for …

Inspired by progress in large-scale language modeling, we apply a similar approach
towards building a single generalist agent beyond the realm of text outputs. The agent …

Continual learning aims to enable a single model to learn a sequence of tasks without
catastrophic forgetting. Top-performing methods usually require a rehearsal buffer to store …

Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements
in many vision tasks in the closed world. However, novel classes emerge from time to time in …

Federated learning has emerged as an important distributed learning paradigm, which
normally involves collaborative updating with others and local updating on private data …

The mainstream paradigm behind continual learning has been to adapt the model
parameters to non-stationary data distributions, where catastrophic forgetting is the central …

Fine-tuning large pre-trained models on downstream tasks has been adopted in a variety of
domains recently. However, it is costly to update the entire parameter set of large pre-trained …

The ability to learn new concepts continually is necessary in this ever-changing world.
However, deep neural networks suffer from catastrophic forgetting when learning new …