3 papers
cs.LG2026
Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment
Ran Liu, Min Yu, Mingqi Liu +7
In dynamic environments, large language models need to keep adapting to new tasks, but continual learning often suffers from forgetting, limited transfer, and vulnerability to adve…
cs.LG2025
Randomized Neural Network with Adaptive Forward Regularization for Online Task-free Class Incremental Learning
Junda Wang, Minghui Hu, Ning Li +2
Class incremental learning (CIL) requires an agent to learn distinct tasks consecutively with knowledge retention against forgetting. Problems impeding the practical applications o…
cs.LG2024
Incremental Online Learning of Randomized Neural Network with Forward Regularization
Junda Wang, Minghui Hu, Ning Li +2
Online learning of deep neural networks suffers from challenges such as hysteretic non-incremental updating, increasing memory usage, past retrospective retraining, and catastrophi…