多模态大模型语言能力易退化？神经元感知的可塑性分配调优带来新解法。
arXiv:2608.08107v1 Announce Type: cross Abstract: Multimodal expansion of large language models (LLMs) enables new perceptual capabilities but often c…
用强化学习驱动的智能体，自动调优操作系统内核参数，突破手动配置瓶颈，释放极致性能。
arXiv:2508.12551v2 Announce Type: replace Abstract: Linux kernel tuning is essential for optimizing operating system (OS) performance, yet remains cha…
arXiv最新论文提出稀疏正交参数调优方法，仅需微调少量正交参数即可有效缓解持续学习中的灾难性遗忘。
arXiv:2411.02813v3 Announce Type: replace Abstract: Continual learning methods based on pre-trained models (PTM) have recently gained attention which …