A central problem in learning from sequential data is representing cumulative history in an incremental fashion as more data is processed. We introduce a general framework (HiPPO) for the online compression of continuous signals and discrete time series by projection onto polynomial bases. Given a measure that specifies the importance of each time step in the past, HiPPO produces an optimal solution to a natural online function approximation problem. As special cases, our framework yields a short derivation of the recent Legendre Memory Unit (LMU) from first principles, and generalizes the ubiquitous gating mechanism of recurrent neural networks such as GRUs. This formal framework yields a new memory update mechanism (HiPPO-LegS) that scales through time to remember all history, avoiding priors on the timescale. HiPPO-LegS enjoys the theoretical benefits of timescale robustness, fast updates, and bounded gradients. By incorporating the memory dynamics into recurrent neural networks, HiPPO RNNs can empirically capture complex temporal dependencies. On the benchmark permuted MNIST dataset, HiPPO-LegS sets a new state-of-the-art accuracy of 98.3%. Finally, on a novel trajectory classification task testing robustness to out-of-distribution timescales and missing data, HiPPO-LegS outperforms RNN and neural ODE baselines by 25-40% accuracy.
Deep Recurrent Stochastic Configuration Networks for Modelling Nonlinear Dynamic Systems
Northeastern University（东北大学）；China University of Mining and Technology（中国矿业大学）；State Key Laboratory of Synthetical Automation for Process Industries（过程综合自动化国家重点实验室）；Research Center for Stochastic Configuration Machines（随机配置机器研究中心）
Clustering and Recognition of Spatiotemporal Features through Interpretable Embedding of Sequence to Sequence Recurrent Neural Networks
Department of Electrical & Computer Engineering（电气与计算机工程系）；Department of Applied Mathematics（应用数学系）；University of Washington（华盛顿大学）；Seattle, WA 98195（西雅图, WA 98195（注意：地址信息按要求不应提取，此处仅为示例说明））
Sensory robustness through top-down feedback and neural stochasticity in recurrent vision models
Hertie Institute for Clinical Brain Research, University of Tübingen（图宾根大学赫蒂临床脑研究所）；University of Tübingen（图宾根大学）；Center for Bionic Intelligence Tübingen Stuttgart (BITS)（图宾根-斯图加特仿生智能中心）；Institute of Cognitive Sciences and Technologies, National Research Council（国家研究委员会认知科学与技术研究所）；Institute of Neurology, University College London（伦敦大学学院神经病学研究所）；German Center for Mental Health (DZPG)（德国心理健康中心）
CITS: Nonparametric Statistical Causal Modeling for High-Resolution Neural Time Series
University of California, San Francisco（旧金山加利福尼亚大学）；UCSF Weill Institute for Neurosciences（旧金山加利福尼亚大学威尔神经科学研究所）；Center for Research on Science and Consciousness（科学与意识研究中心）；National University of Singapore（新加坡国立大学）；Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco（旧金山加利福尼亚大学生物工程与治疗科学系）
Video Latent Flow Matching: Optimal Polynomial Projections for Video Interpolation and Extrapolation
Wyoming Seminary（怀俄明神学院）；Simons Institute for the Theory of Computing, University of California, Berkeley（加州大学伯克利分校西蒙斯理论计算研究所）；Sun Yat-sen University（中山大学）
本文提出 Video Latent Flow Matching (VLFM)，利用预训练图像生成模型和 HiPPO 最优多项式投影建模潜在块流，实现任意帧率的视频插值与外推生成，并具备理论逼近误差和时间尺度鲁棒性优势。
Self-Organizing Recurrent Stochastic Configuration Networks for Nonstationary Data Modelling
Northeastern University（东北大学）；China University of Mining and Technology（中国矿业大学）；State Key Laboratory of Synthetical Automation for Process Industries（流程工业综合自动化国家重点实验室）；Research Center for Stochastic Configuration Machines（随机配置机器研究中心）
Neural-network acceleration of projection-based model-order-reduction for finite plasticity: Application to RVEs
University of Luxembourg, Faculty of Science, Technology and Medicine（卢森堡大学科学、技术与医学学院）；University of Liege（列日大学）；Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）
Scalable Adaptive Stochastic Optimization Using Random Projections
Institute for Machine Learning, Department of Computer Science, ETH Zürich（苏黎世联邦理工学院计算机科学系机器学习研究所）；Seminar for Statistics, Department of Mathematics, ETH Zürich（苏黎世联邦理工学院数学系统计研讨班）；Disney Research, Zürich（迪士尼研究院苏黎世分院）
On Orthogonal Recurrent Neural Networks Quantization
Institut de Mathématiques de Toulouse（图卢兹数学研究所）；Université de Toulouse（图卢兹大学）；CNRS（法国国家科学研究中心）；UPS IMT；Institut de Recherche Technologique Saint Exupéry（圣埃克苏佩里技术研究院）
Recurrent Stochastic Configuration Networks for Temporal Data Analytics
State Key Laboratory of Synthetical Automation for Process Industries（流程工业综合自动化国家重点实验室）；Northeastern University（东北大学）；Research Center for Stochastic Configuration Machines（随机配置机器研究中心）；China University of Mining and Technology（中国矿业大学）
Dispersion based Recurrent Neural Network Model for Methane Monitoring in Albertan Tailings Ponds
Interdisciplinary Lab for Mathematical Ecology and Epidemiology (ILMEE) & The Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton (AB), T6G 2J5, Canada（跨学科生态与流行病学实验室（ILMEE）及阿尔伯塔大学数学与统计科学系）；The Department of Mathematics and Computer Science, University of Richmond, Richmond (VA), 23173, United States（里士满大学数学与计算机科学系）
Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks
School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；School of Public Health, Peking University（北京大学公共卫生学院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；Peng Cheng Laboratory（鹏城实验室）
