自2025年初DeepSeek R1模型发布以来，强化学习（RL）在大型语言模型（LLM）的后训练范式中受到越来越多的关注，R1的突破性在于引入了可验证奖励强化学习（RLVR），通过构建数学题、代码谜题等自动验证环境，使模型在客观奖励信号的驱动下，自发地演化出与人类推理策略高度相似的思维方式。

Abstract: This article proposes an inverse design method based on numerical Green’s function (NGF-IDM) to achieve the intelligent and efficient design of waveguide devices. Inspired by the metal ...

Abstract: Mobile Edge Computing (MEC) is a key technology for delivering low-latency services to mobile and edge devices, supporting applications like autonomous vehicles and smart cities. However, ...

Drug resistance poses a significant challenge to cancer treatment, often caused by intratumor heterogeneity. Combination therapies have shown to be an effective strategy to prevent resistant cancer ...