Numerical approximations of partial differential equations (PDEs) are routinely employed to formulate the solution of physics, engineering, and mathematical problems involving functions of several variables, such as the propagation of heat or sound, fluid flow, elasticity, electrostatics, electrodynamics, and more. While this has led to solving many complex phenomena, there are some limitations. Conventional approaches such as Finite Element Methods (FEMs) and Finite Difference Methods (FDMs) require considerable time and are computationally expensive. In contrast, data-driven machine learning-based methods, such as neural networks, provide a faster, fairly accurate alternative, and, in particular, focus on neural operators, which have certain advantages such as discretization invariance and resolution invariance. This article aims to provide a comprehensive insight into how data-driven approaches can complement conventional techniques to solve engineering and physics problems, while also noting some of the open problems of machine learning-based approaches. We will note how these new computational approaches can bring immense advantages in tackling many problems in fundamental and applied physics.
F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning
School of Computing and Data Science, The University of Hong Kong（计算与数据科学学院，香港大学）；Institute for AI Industry Research, Tsinghua University（人工智能产业研究院，清华大学）；Beihang University（北航大学）
Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
University of Minnesota（明尼苏达大学）；University of Cincinnati（辛辛那提大学）；Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院）；Northeastern University（东北大学）；North Carolina State University（北卡罗来纳州立大学）
To think inside the box, or to think out of the box? Scientific discovery via the reciprocation of insights and concepts
Peking University（北京大学）；PersLEARN
如果说科学发现是人类进步的主要驱动力之一，那么洞察力就是这台发动机的燃料，长期以来，这台发动机一直吸引着行为层面的研究来理解和模拟其潜在的认知过程。然而，目前对科学发现进行抽象的任务大多集中在顿悟的出现上，而忽视了领域知识所发挥的特殊作用。在这篇概念论文中，我们将科学发现视为积极寻求有见地的解决方案的$thinking \ out \ of \ the \ box$与概括概念领域知识以保持正确的$thinking \ inside \ the \ box$之间的相互作用。因此，我们提出了Mindle，一个语义搜索游戏，触发科学发现一样的思维自发，作为基础设施，探索科学发现的大规模。在此基础上，我们可以进一步研究洞察力的元策略和概念的使用。在试点研究中，几个有趣的观察启发了详细的假设元策略，上下文和个人的多样性进行进一步的调查。
Next-Generation Simulation Illuminates Scientific Problems of Organised Complexity
Tongji University（同济大学）；Key Laboratory of Embedded System and Service Computing, Ministry of Education（嵌入式系统与服务计算教育部重点实验室）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Functional Programming Paradigm of Python for Scientific Computation Pipeline Integration
Shenzhen United Imaging Research Institute of Innovative Medical Equipment（深圳联合创新医疗设备研究院）；United Imaging Healthcare Inc.（联影医疗）；Institute for Medical Imaging Technology, Shanghai Jiao Tong University School of Medicine, United Imaging Healthcare（上海交通大学医学院医学影像技术研究所、联影医疗）
Towards a new paradigm of scientific discovery with socialized artificial intelligence
Baize Research（白泽研究院）；Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院）；Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology（昆明理工大学云南省人工智能重点实验室）；School of Automation, Southeast University（东南大学自动化学院）；School of Artificial Intelligence, Tianjin University（天津大学人工智能学院）；School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机学院）；SeetaCloud Technology（思特云科技）；GPUhub Pte. Ltd.（GPUhub私人有限公司）
Physics-aware Machine Learning Revolutionizes Scientific Paradigm for Machine Learning and Process-based Hydrology
Technical University of Munich（慕尼黑工业大学）；School of Engineering and Design, Technical University of Munich（慕尼黑工业大学工程与设计学院）；School of Geographical Sciences, University of Bristol（布里斯托大学地理科学学院）；Ludwig-Maximilians-University（路德维希-马克西米利安-慕尼黑大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）
Zeroth-Order SciML: Non-intrusive Integration of Scientific Software with Deep Learning
University of Minnesota（明尼苏达大学）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）；Michigan State University（密歇根州立大学）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）
Scientific intuition inspired by machine learning generated hypotheses
University of Toronto（多伦多大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Vector Institute for Artificial Intelligence（矢量人工智能研究所）；National Research Council of Canada（加拿大国家研究委员会）；Canadian Institute for Advanced Research (CIFAR)（加拿大高等研究院）
BloClaw: An Omniscient, Multi-Modal Agentic Workspace for Next-Generation Scientific Discovery
AI Innovation Department, Beijing 1st Biotech Group Co., Ltd.（北京第一生物技术集团有限公司AI创新部）；Diplomatic Negotiation Simulation and Data Lab（外交谈判模拟与数据实验室）；First Medical Center, Chinese PLA General Hospital（中国人民解放军总医院第一医学中心）
Multimodal Deep Learning for Scientific Imaging Interpretation
Science and Technology Division, Corning Incorporated（康宁公司科技事业部）；Robert Frederick Smith School of Chemical and Biomolecular Engineering, Cornell University（康奈尔大学罗伯特·弗雷德里克·史密斯化学与生物分子工程学院）
本文提出多模态深度学习框架 GlassLLaVA，结合论文图文数据与 GPT-4，实现玻璃材料 SEM 图像的类人解释、特征识别和缺陷检测，并建立可对照研究答案的评估指标。
Agent4S: The Transformation of Research Paradigms from the Perspective of Large Language Models
Beijing National Laboratory for Condensed Matter Physics, Institute of Physics, Chinese Academy of Sciences（北京凝聚态物理国家实验室，物理研究所，中国科学院）；School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Science（中国科学院大学先进交叉学科学院）；Beijing Gongyu Zhiyan Technology Co., Ltd（北京公誉智研科技有限公司）；Key Laboratory of Optical Astronomy, National Astronomical Observatories, Chinese Academy of Sciences（光学天文重点实验室，国家天文台，中国科学院）；College of Astronomy and Space Sciences, University of Chinese Academy of Sciences（中国科学院大学天文与空间科学学院）；State Key Laboratory of Isotope Geochemistry, Guangzhou Institute of Geochemistry, Chinese Academy of Sciences（同位素地球化学国家重点实验室，广州地球化学研究所，中国科学院）；College of Earth and Planetary Sciences, University of Chinese Academy of Sciences（中国科学院大学地球与行星科学学院）；Alibaba Cloud, Hangzhou, Zhejiang, China（阿里云，杭州，浙江，中国）；College of Information and Engineering, Wenzhou Medical University（温州医学院信息与工程学院）；Wenzhou Institute, University of Chinese Academy of Sciences（温州研究所，中国科学院大学）；Department of science and development, Chinese academy of sciences, Beijing, China（科学与发展部门，中国科学院，北京，中国）
FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration
University of Chinese Academy of Sciences（中国科学院大学）；Dalian University of Technology（大连理工大学）；UNSW Sydney（新南威尔士大学悉尼分校）；Shenzhen University of Advanced Technology（深圳理工大学）；Xiamen University（厦门大学）
Google（谷歌）；Google DeepMind（谷歌DeepMind）；University of Chicago（芝加哥大学）；CUNEF Universidad（西班牙金融研究大学）；MIT FutureTech（麻省理工学院未来科技）；University of Oxford（牛津大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Pennsylvania（宾夕法尼亚大学）
