研究人员正在开发新颖的方法来解决持续学习中的灾难性遗忘问题，即人工智能模型在学习新任务时会丢失先前获得的知识。最近几篇 arXiv 论文提出了不同的方法，包括规范化多模态学习中的模态贡献漂移、采用参数高效门控适应以及利用无梯度进化算法。其他方法则侧重于具有无梯度路由的紧凑型潜在空间适配器，以及在零空间中优化状态空间模型以在顺序任务中保留知识。
AI
arXiv:2607.27260v1 Announce Type: new Abstract: Multimodal continual learning (MMCL) aims to learn emerging knowledge from multimodal data while preserving knowledge. To mitigate forgetting, current MMCL methods usually focus on cross-modal representation alignment or semantic si…
arXiv cs.LG
TIER_1English(EN)·Yuyang Liu, Qiuhe Hong, Linlan Huang, Alexandra Gomez-Villa, Dipam Goswami, Tiantian Peng, Xialei Liu, Joost van de Weijer, Yonghong Tian·
arXiv:2508.04227v3 Announce Type: replace-cross Abstract: Vision-language models (VLMs), spanning predictive architectures to generative Multimodal Large Language Models (MLLMs), have revolutionized artificial intelligence through powerful cross-modal alignment and zero-shot gene…
arXiv:2607.26523v1 Announce Type: new Abstract: We introduce CMP (Cognitive Memory Primitive), a continual-learning architecture that repre?sents inputs as sparse relational codes, stores them in a two-tier competitive memory, and learns through local updates without end-to-end b…
arXiv:2603.10046v2 Announce Type: replace Abstract: 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). C…
arXiv:2504.01219v2 Announce Type: replace Abstract: Neural networks are notorious for forgetting old skills when taught new ones - a problem known as catastrophic forgetting. Standard continual learning techniques try to fix this by saving old data or relying on complex gradient …
arXiv:2607.23837v1 Announce Type: cross Abstract: Large language models generalize well to individual tasks but lack an inherent mechanism for learning them sequentially, leading to catastrophic forgetting. To mitigate this, LoRA-based continual learning methods allocate a separa…
arXiv:2411.15469v3 Announce Type: replace Abstract: Continual Learning (CL) aims to equip AI models with the ability to learn a sequence of tasks over time, without forgetting previously learned knowledge. Recently, State Space Models (SSMs), particularly the Mamba model, have ac…
