新基准Imaging-101系统评估LLM编码代理在科学计算成像上的表现，揭示当前模型能力边界。
arXiv:2607.10789v1 Announce Type: new Abstract: Computational imaging, which recovers hidden signals from indirect, noisy measurements, underpins quan…
将机器学习与偏微分方程结合，用算子学习破解周期域上的三次非线性薛定谔方程，开启科学计算新范式。
arXiv:2606.27459v1 Announce Type: new Abstract: We consider the cubic nonlinear Schr\"odinger (NLS) equation on two-dimensional flat tori with varying…
李对称性赋能科学计算，新型求解器提升PDE学习精度与效率。
arXiv:2510.25731v2 Announce Type: replace-cross Abstract: Initial-boundary value problems (IBVPs) provide the essential framework for modelling a wide…
IT之家 6 月 23 日消息，NVIDIA（英伟达）当地时间 22 日宣布，基于 Vera Rubin NVL4 平台的系统预计将于 2026Q4 通过全球系统制造商上市。 Vera Rubin NVL4“托盘” 结合了 4 颗 Rubin GPU 和 2 颗 Vera CPU ，GPU-GPU …
用GPT做物理探测器模拟？论文提出条件自回归生成方法，加速CLAS12探测器响应仿真，AI与高能物理的跨界创新。
arXiv:2606.16035v1 Announce Type: cross Abstract: Modern particles physics experiments have demonstrated an increasing need for fast, high-fidelity de…
Wolfram Language 15 新版本发布，专为人类与AI智能体打造的强大计算语言，值得开发者关注。
Computational language built for humans and AI agents Discussion | Link
利用agentic AI自动化HPC遗留代码的并行化与迁移，为科研软件工程提速。
arXiv:2606.08710v1 Announce Type: cross Abstract: Modernization of legacy scientific codes is often necessary to keep up with the ever-evolving change…
大模型自动化翻译遗留科学代码为可微分框架，直接应用于地表模型，为科学计算现代化提供系统方案
arXiv:2606.07681v1 Announce Type: cross Abstract: Differentiable programming offers transformative capabilities for scientific modeling, enabling grad…
用神经网络逼近非线性动力系统，并给出严格误差上界认证，让AI黑箱变透明。
arXiv:2505.15497v3 Announce Type: replace Abstract: Neural networks hold great potential to act as approximate models of nonlinear dynamical systems, …
引入损失条件机制优化PINNs训练，高效求解参数化偏微分方程族
arXiv:2606.04420v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) approximate solutions of ODEs and PDEs by minimising a weight…
在谱空间融合物理信息的扩散模型，提升科学计算中生成数据的物理一致性与精度。
arXiv:2602.09708v2 Announce Type: replace-cross Abstract: We propose physics-informed spectral diffusion (PISD), a methodology that combines generativ…
揭示物理信息神经网络（PINNs）失败的根本原因——过拟合，为改进PINN训练提供新视角
arXiv:2605.30910v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) are a common class of machine learning-based partial differen…
虚拟细胞自主推理新突破，让AI像科学家一样理解细胞机制。
arXiv:2604.11661v3 Announce Type: replace Abstract: Large language models (LLMs) have recently gained significant attention as a promising approach to…
用机器学习加速FARICH探测器响应模拟，为高能物理研究提供高效新方案。
arXiv:2605.17635v1 Announce Type: cross Abstract: A fast simulation of the detector response is a vital task in high-energy physics (HEP). Traditional…