Recent advances of foundation language models-based continual learning: A survey

Y Yang, J Zhou, X Ding, T Huai, S Liu, Q Chen… - ACM Computing …, 2025‏ - dl.acm.org
Recently, foundation language models (LMs) have marked significant achievements in the
domains of natural language processing and computer vision. Unlike traditional neural …

[PDF][PDF] Recurrent concept drifts on data streams

N Gunasekara, B Pfahringer, HM Gomes… - Proceedings of the …, 2024‏ - researchgate.net
In an era where machine learning permeates every facet of human existence, and data
evolves incessantly, the application of machine learning models transcends mere data …

Towards General Industrial Intelligence: A Survey on IIoT-Enhanced Continual Large Models

J Chen, J He, F Chen, Z Lv, J Tang, W Li, Z Liu… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Currently, most applications in the Industrial Internet of Things (IIoT) still rely on CNN-based
neural networks. Although Transformer-based large models (LMs), including language …

State-space modeling in long sequence processing: A survey on recurrence in the transformer era

M Tiezzi, M Casoni, A Betti, M Gori… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Effectively learning from sequential data is a longstanding goal of Artificial Intelligence,
especially in the case of long sequences. From the dawn of Machine Learning, several …

Detecting evolving fraudulent behavior in online payment services: Open-category and concept-drift

H Zhu, C Wang, S Chai - IEEE Transactions on Services …, 2024‏ - ieeexplore.ieee.org
The convenience offered by the Internet accelerates the evolution of fraudulent behavior
during facilitating the rapid development of online payment services. Fraudsters can change …

Managing the unknown: a survey on open set recognition and tangential areas

M Barcina-Blanco, JL Lobo, P Garcia-Bringas… - arxiv preprint arxiv …, 2023‏ - arxiv.org
In real-world scenarios classification models are often required to perform robustly when
predicting samples belonging to classes that have not appeared during its training stage …

[HTML][HTML] Continual Learning for Time Series Forecasting: A First Survey

Q Besnard, N Ragot - Engineering Proceedings, 2024‏ - mdpi.com
Deep learning has brought significant advancements in the field of artificial intelligence,
particularly in robotics, imaging, sound processing, etc. However, a common major …