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 …

Federated learning (FL) has drawn increasing attention owing to its potential use in large-
scale industrial applications. Existing FL works mainly focus on model homogeneous …

Language is essentially a complex, intricate system of human expressions governed by
grammatical rules. It poses a significant challenge to develop capable AI algorithms for …

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 …

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 …

Building models that can be rapidly adapted to novel tasks using only a handful of annotated
examples is an open challenge for multimodal machine learning research. We introduce …

Test-time domain adaptation aims to adapt a source pre-trained model to a target domain
without using any source data. Existing works mainly consider the case where the target …

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 …

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 …

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