研究人员正在探索新的方法来改进AI系统的持续学习能力，重点关注模型如何从顺序经验中学习而不遗忘过去的知识。新的基准，如CL-Bench，正在被开发出来，以严格评估这些系统在不同领域的表现。论文还介绍了参数高效微调的TailLoR等新颖技术，并将灾难性遗忘重新定义为可访问性问题而非知识擦除。 AI
影响 持续学习的进步可能带来更具适应性和效率的AI系统，这些系统可以在真实、动态的环境中持续学习。
排序理由 多篇研究论文在arXiv上发表，介绍了AI持续学习的新基准、方法和理论框架。
AI 生成摘要 · Google Gemini · 来自 13 个来源。 我们如何撰写摘要 →
arXiv:2606.05661v1 Announce Type: cross Abstract: Continual learning, the ability of AI systems to improve through sequential experience, has attracted substantial interest, but no high-quality benchmark exists to evaluate it. We introduce Continual Learning Bench (CL-Bench), the…
arXiv:2606.06494v1 Announce Type: new Abstract: Parameter-efficient finetuning methods based on spectral decomposition have enabled progress in Continual Learning. In this paper we introduce TailLoR, which utilizes the singular bases U and V of the pre-trained weights as a fixed …
arXiv:2606.06032v1 Announce Type: new Abstract: Catastrophic forgetting is commonly interpreted as the irreversible erasure of previously acquired knowledge during sequential learning. In this work, we investigate an alternative perspective: that forgetting may arise not from com…
arXiv:2606.05695v1 Announce Type: new Abstract: Exemplar-free class-incremental learning (EFCIL) aims to acquire new classes over time without storing raw data. Historically, prototype rehearsal, which samples around stored class prototypes and mixes them with current-task data, …
arXiv:2606.05559v1 Announce Type: new Abstract: Deployed large language model agents must adapt to distribution shift in dynamic environments. Ideally, adaptation can be performed from accumulated agent experiences and retain prior capabilities while transferring to future tasks.…
Parameter-efficient finetuning methods based on spectral decomposition have enabled progress in Continual Learning. In this paper we introduce TailLoR, which utilizes the singular bases U and V of the pre-trained weights as a fixed reference frame to learn a low-rank update appli…
Catastrophic forgetting is commonly interpreted as the irreversible erasure of previously acquired knowledge during sequential learning. In this work, we investigate an alternative perspective: that forgetting may arise not from complete destruction of task representations but fr…
arXiv:2606.03843v1 Announce Type: cross Abstract: Continual learning methods aim to maximize the stability and plasticity of machine learning models that are trained on a sequence of tasks. The standard measure of stability (i.e., forgetting) is the 0-shot performance of a model …
Continual learning methods aim to maximize the stability and plasticity of machine learning models that are trained on a sequence of tasks. The standard measure of stability (i.e., forgetting) is the 0-shot performance of a model on previously learned tasks, and plasticity, the p…
arXiv:2511.09190v2 Announce Type: replace Abstract: Hyperparameter Optimization (HPO) can lift the burden of tuning hyperparameters (HPs) of neural networks. HPO algorithms from the Population Based Training (PBT) family are efficient thanks to dynamically adjusting HPs every few…
arXiv:2606.01863v1 Announce Type: new Abstract: Continual learning struggles to balance retaining past knowledge with absorbing new tasks. Stefan-CL elegantly resolves this stability-plasticity dilemma through the physics of melting. It frames consolidated knowledge as a protecte…
arXiv:2606.01379v1 Announce Type: new Abstract: While prompt-based parameter-efficient continual learning mitigates catastrophic forgetting by isolating task-specific prompts, this isolation also limits later tasks from improving earlier ones, leaving backward knowledge transfer …
arXiv:2605.19145v2 Announce Type: replace Abstract: In the literature, many continual learning (CL) algorithms have been proposed to address the issue of catastrophic forgetting in ML models (i.e., learning new tasks leads to the loss of performance on previously learned tasks). …