Analog front-end design heavily relies on specialized human expertise and costly trial-and-error simulations, which motivated many prior works on analog design automation. However, efficient and effective exploration of the vast and complex design space remains constrained by the time-consuming nature of SPICE simulations, making effective design automation a challenging endeavor. In this paper, we introduce INSIGHT, a GPU-powered, technology-agnostic, effective universal neural simulator in the analog front-end design automation loop. INSIGHT accurately predicts the performance metrics of analog circuits across various technologies with just a few microseconds of inference time. Notably, its autoregressive capabilities enable INSIGHT to accurately predict simulation-costly critical transient specifications leveraging less expensive performance metric information. The low cost and high fidelity feature make INSIGHT a good substitute for standard simulators in analog front-end optimization frameworks. INSIGHT is compatible with any optimization framework, facilitating enhanced design space exploration for sample efficiency through sophisticated offline learning and adaptation techniques. Our experiments demonstrate that INSIGHT-M, a model-based batch reinforcement learning sizing framework with INSIGHT as the accurate surrogate, only requires < 20 real-time simulations with 100-1000x lower simulation costs and significant speedup over existing sizing methods.
Generative AI for End-to-End Limit Order Book Modelling: A Token-Level Autoregressive Generative Model of Message Flow Using a Deep State Space Network
University of Oxford(牛津大学);Oxford-Man Institute of Quantitative Finance(牛津-曼量化金融研究院);Alan Turing Institute(艾伦·图灵研究所);Man Group(英仕曼集团);Foerster Lab for AI Research(福斯特人工智能研究实验室)
Mixed neural posterior estimation for simulators with discrete and continuous parameters
appliedAI Institute for Europe(appliedAI欧洲研究院);Machine Learning in Science, University of Tübingen(图宾根大学机器学习科学系);Tübingen AI Center(图宾根人工智能中心);Hertie Institute for AI in Brain Health, University of Tübingen(图宾根大学脑健康人工智能研究院);Max Planck Institute for Intelligent Systems(智能系统马克斯·普朗克研究所);Max Planck Institute for Biological Intelligence(生物智能马克斯·普朗克研究所)
Harnessing Vision Models for Time Series Analysis: A Survey
University of Houston(德克萨斯大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Connecticut(康涅狄格大学);NEC Laboratories America(日本 NEC 美国实验室);Florida International University(佛罗里达国际大学)
Equivariant Neural Simulators for Stochastic Spatiotemporal Dynamics
Data and Artificial Intelligence Cluster, Eindhoven University of Technology(埃因霍温理工大学数据与人工智能集群);Swiss Plasma Center, École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院瑞士等离子体中心)
Autoregressive deep learning for real-time simulation of soft tissue dynamics during virtual neurosurgery
Research Unit Medical Informatics(医学信息学研究单元);RISC Software GmbH(RISC软件公司);Emmi AI GmbH;ELLIS Unit Linz(林茨ELLIS单元);Institute for Machine Learning(机器学习研究所);JKU Linz(林茨JKU)
BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction
City University of Hong Kong(香港城市大学);University of Victoria(维多利亚大学);Hon Hai Research Institute(鸿海研究院);Carnegie Mellon University(卡内基梅隆大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
BRICKS: Compositional Neural Markov Kernels for Zero-Shot Radiation-Matter Simulation
Technical University of Munich(慕尼黑技术大学);Max-Planck Institute for Mathematics in the Sciences(马克斯·普朗克数学研究所);SLAC National Accelerator Laboratory(斯坦福直线加速器实验室);Haifa University(海法大学);Department of Physics(物理系);Indian Institute of Technology, Kanpur(印度理工学院坎普尔分校);Munich Center for Machine Learning(慕尼黑机器学习中心)