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 …

The recent success of large language models (LLMs) trained on static, pre-collected,
general datasets has sparked numerous research directions and applications. One such …

Continual Learning (CL) aims to sequentially train models on streams of incoming data that
vary in distribution by preserving previous knowledge while adapting to new data. Current …

Distribution shifts occur when the test distribution differs from the training distribution, and
can considerably degrade performance of machine learning models deployed in the real …

Abstract Current evaluations of Continual Learning (CL) methods typically assume that there
is no constraint on training time and computation. This is an unrealistic assumption for any …

Continual learning (CL) is widely regarded as crucial challenge for lifelong AI. However,
existing CL benchmarks, eg Permuted-MNIST and Split-CIFAR, make use of artificial …

Online continual learning aims to get closer to a live learning experience by learning directly
on a stream of data with temporally shifting distribution and by storing a minimum amount of …

In this paper we describe the design and the ideas motivating a new Continual Learning
benchmark for Autonomous Driving (CLAD), that focuses on the problems of object …

Concept drift is one of the most frustrating challenges for learning-based security
applications built on the closeworld assumption of identical distribution between training and …

Novel view synthesis aims to render unseen views given a set of calibrated images. In
practical applications, the coverage, appearance or geometry of the scene may change over …