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 …

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 …

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

The goal of continual learning is to improve the performance of recognition models in
learning sequentially arrived data. Although most existing works are established on the …

Prompt-based continual learning is an emerging direction in leveraging pre-trained
knowledge for downstream continual learning, and has almost reached the performance …

Continual learning (CL) aims to incrementally learn different tasks (such as classification) in
a non-stationary data stream without forgetting old ones. Most CL works focus on tackling …

Existing work in continual learning (CL) focuses on mitigating catastrophic forgetting, ie,
model performance deterioration on past tasks when learning a new task. However, the …

Recent work on large language models relies on the intuition that most natural language
processing tasks can be described via natural language instructions. Language models …

Pre-training is prevalent in nowadays deep learning to improve the learned model's
performance. However, in the literature on federated learning (FL), neural networks are …