让大模型像人类一样学习记忆管理，将文件系统操作变为可训练的认知技能
arXiv:2607.01224v1 Announce Type: new Abstract: Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize kno…
提出可训练的平滑旋转变换与学习通道缩放，为LLM量化精度提升提供新思路
arXiv:2606.09927v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is one of the most practical ways to reduce the serving cost of Lar…
探究IQP量子电路生发机在高斯初始化下的可训练性，为量子生成模型提供新视角。
arXiv:2606.10179v1 Announce Type: cross Abstract: Quantum Circuit Born Machines (QCBMs) offer a natural approach to generative machine learning by lev…
当智能感知成为一种可训练的超材料特性，物理与AI的边界被重新定义。
arXiv:2605.23967v1 Announce Type: cross Abstract: In biological systems, sensing is not performed by the brain alone: the body deforms, vibrates, and …
量子机器学习新突破：可训练频率电路用更少编码门实现高频近似，优化变分量子电路效率。
arXiv:2602.23409v2 Announce Type: replace-cross Abstract: Angle-encoded variational quantum circuits admit a truncated Fourier series representation o…