Related papers: Grow, Assess, Compress: Adaptive Backbone Scaling …

Incremental Learning (IL) is useful when artificial systems need to deal with streams of data and do not have access to all data at all times. The most challenging setting requires a constant complexity of the deep model and an incremental…

Class-incremental learning (CIL) requires deep learning models to continuously acquire new knowledge from streaming data while preserving previously learned information. Recently, CIL based on pre-trained models (PTMs) has achieved…

Class-incremental learning (CIL) aims to continuously introduce novel categories into a classification system without forgetting previously learned ones, thus adapting to evolving data distributions. Researchers are currently focusing on…

Few-shot class-incremental learning (FSCIL), which targets at continuously expanding model's representation capacity under few supervisions, is an important yet challenging problem. On the one hand, when fitting new tasks (novel classes),…

Continual Learning (CL) epitomizes an advanced training paradigm wherein prior data samples remain inaccessible during the acquisition of new tasks. Numerous investigations have delved into leveraging a pre-trained Vision Transformer (ViT)…

Existing reasoning data curation pipelines score whole samples, treating every intermediate step as equally valuable. In reality, steps within a trace contribute very unevenly, and selecting reasoning data well requires assessing them…

Constrained Reinforcement Learning (CRL) aims to maximize cumulative rewards while satisfying constraints. However, existing CRL algorithms often encounter significant constraint violations during training, limiting their applicability in…

Class incremental semantic segmentation (CISS) aims to segment new classes during continual steps while preventing the forgetting of old knowledge. Existing methods alleviate catastrophic forgetting by replaying distributions of previously…

Continual Knowledge Graph Embedding (CKGE) aims to efficiently learn new knowledge and simultaneously preserve old knowledge. Dominant approaches primarily focus on alleviating catastrophic forgetting of old knowledge but neglect efficient…

Learning continually is a key aspect of intelligence and a necessary ability to solve many real-life problems. One of the most effective strategies to control catastrophic forgetting, the Achilles' heel of continual learning, is storing…

Exemplar-Free Class Incremental Learning (efCIL) aims to continuously incorporate the knowledge from new classes while retaining previously learned information, without storing any old-class exemplars (i.e., samples). For this purpose,…

Motivated by the efficiency and rapid convergence of pre-trained models for solving downstream tasks, this paper extensively studies the impact of Continual Learning (CL) models as pre-trainers. In both supervised and unsupervised CL, we…

Wearable sensors in Internet of Things (IoT) ecosystems increasingly support applications such as remote health monitoring, elderly care, and smart home automation, all of which rely on robust human activity recognition (HAR). Continual…

In federated healthcare systems, Federated Class-Incremental Learning (FCIL) has emerged as a key paradigm, enabling continuous adaptive model learning among distributed clients while safeguarding data privacy. However, in practical…

Continual Imitation Learning (CiL) involves extracting and accumulating task knowledge from demonstrations across multiple stages and tasks to achieve a multi-task policy. With recent advancements in foundation models, there has been a…

Continual learning aims to acquire new knowledge while retaining past information. Class-incremental learning (CIL) presents a challenging scenario where classes are introduced sequentially. For video data, the task becomes more complex…

A fundamental requirement for intelligent systems is the ability to learn continuously under changing environments. However, models trained in this regime often suffer from catastrophic forgetting. Leveraging pre-trained models has recently…

Simulation-based design space exploration (DSE) aims to efficiently optimize high-dimensional structured designs under complex constraints and expensive evaluation costs. Existing approaches, including heuristic and multi-step reinforcement…

Class-Incremental Learning (CIL) requires a model to continually learn new classes without forgetting old ones. A common and efficient solution freezes a pre-trained model and employs lightweight adapters, whose parameters are often forced…

Ensemble models achieve state-of-the-art performance on prediction tasks, but usually require aggregating a large number of weak learners. This can hinder deployment, interpretability, and downstream tasks such as robustness verification.…