{"list":"other","total":65,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"2106.13008","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","created":"2021-06-24","cited_by_count":1676},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"2310.10688","title":"A decoder-only foundation model for time-series forecasting","created":"2023-10-14","cited_by_count":692},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"id":"1712.09707","title":"Deep learning for universal linear embeddings of nonlinear dynamics","created":"2017-12-27","cited_by_count":494},{"id":"2102.12086","title":"Modern Koopman Theory for Dynamical Systems","created":"2021-02-24","cited_by_count":276},{"id":"2308.08241","title":"TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series","created":"2023-08-16","cited_by_count":169},{"id":"2406.16964","title":"Are Language Models Actually Useful for Time Series Forecasting?","created":"2024-06-22","cited_by_count":168},{"id":"1802.07486","title":"Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks","created":"2018-02-21","cited_by_count":155},{"id":"1712.01378","title":"Linearly-Recurrent Autoencoder Networks for Learning Dynamics","created":"2017-12-04","cited_by_count":145},{"id":"1711.05501","title":"Sparse identification of nonlinear dynamics for model predictive control in the low-data limit","created":"2017-11-15","cited_by_count":140},{"id":"2306.09364","title":"TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting","created":"2023-06-14","cited_by_count":139},{"id":"2401.03955","title":"Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series","created":"2024-01-08","cited_by_count":127},{"id":"2003.02236","title":"Forecasting Sequential Data using Consistent Koopman Autoencoders","created":"2020-03-04","cited_by_count":115},{"id":"2010.03957","title":"Transformers for Modeling Physical Systems","created":"2020-10-04","cited_by_count":106},{"id":"2410.10469","title":"Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts","created":"2024-10-14","cited_by_count":95},{"id":"2110.05266","title":"Chaos as an interpretable benchmark for forecasting and data-driven modelling","created":"2021-10-11","cited_by_count":88},{"id":"2410.18959","title":"Context is Key: A Benchmark for Forecasting with Essential Textual Information","created":"2024-10-24","cited_by_count":87},{"id":"2110.07238","title":"On the difficulty of learning chaotic dynamics with RNNs","created":"2021-10-14","cited_by_count":67},{"id":"2305.12907","title":"Meta-in-context learning in large language models","created":"2023-05-22","cited_by_count":59},{"id":"2306.04406","title":"Generalized Teacher Forcing for Learning Chaotic Dynamics","created":"2023-06-07","cited_by_count":58},{"id":"2203.10716","title":"Forecast Evaluation for Data Scientists: Common Pitfalls and Best Practices","created":"2022-03-21","cited_by_count":55},{"id":"2202.01889","title":"Generalizing to New Physical Systems via Context-Informed Dynamics Model","created":"2022-02-01","cited_by_count":50},{"id":"2402.10835","title":"Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities","created":"2024-02-16","cited_by_count":48},{"id":"2306.01187","title":"Training neural operators to preserve invariant measures of chaotic attractors","created":"2023-06-01","cited_by_count":46},{"id":"2402.18819","title":"Dual Operating Modes of In-Context Learning","created":"2024-02-29","cited_by_count":43},{"id":"1902.07186","title":"Identifying nonlinear dynamical systems via generative recurrent neural networks with applications to fMRI","created":"2019-02-19","cited_by_count":41},{"id":"2110.04744","title":"Long Expressive Memory for Sequence Modeling","created":"2021-10-10","cited_by_count":41},{"id":"2106.04546","title":"LEADS: Learning Dynamical Systems that Generalize Across Environments","created":"2021-06-08","cited_by_count":40},{"id":"2210.03675","title":"Koopman Neural Forecaster for Time Series with Temporal Distribution Shifts","created":"2022-10-07","cited_by_count":37},{"id":"2207.02542","title":"Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems","created":"2022-07-06","cited_by_count":36},{"id":"2207.00521","title":"Using Machine Learning to Anticipate Tipping Points and Extrapolate to Post-Tipping Dynamics of Non-Stationary Dynamical Systems","created":"2022-07-01","cited_by_count":33},{"id":"2402.18377","title":"Out-of-Domain Generalization in Dynamical Systems Reconstruction","created":"2024-02-28","cited_by_count":33},{"id":"2201.08910","title":"A Systematic Exploration of Reservoir Computing for Forecasting Complex Spatiotemporal Dynamics","created":"2022-01-21","cited_by_count":30},{"id":"2402.04467","title":"DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems","created":"2024-02-06","cited_by_count":30},{"id":"2409.15771","title":"Zero-shot forecasting of chaotic systems","created":"2024-09-24","cited_by_count":28},{"id":"2303.08011","title":"Model scale versus domain knowledge in statistical forecasting of chaotic systems","created":"2023-03-13","cited_by_count":27},{"id":"1612.07846","title":"A State Space Approach for Piecewise-Linear Recurrent Neural Networks for Reconstructing Nonlinear Dynamics from Neural Measurements","created":"2016-12-23","cited_by_count":25},{"id":"2311.04128","title":"Generative learning for nonlinear dynamics","created":"2023-11-07","cited_by_count":22},{"id":"2005.13232","title":"Sparse Identification of Nonlinear Dynamical Systems via Reweighted $\\ell_1$-regularized Least Squares","created":"2020-05-27","cited_by_count":21},{"id":"2410.14240","title":"Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction","created":"2024-10-18","cited_by_count":19},{"id":"2009.04278","title":"DyNODE: Neural Ordinary Differential Equations for Dynamics Modeling in Continuous Control","created":"2020-09-09","cited_by_count":18},{"id":"2310.17561","title":"Bifurcations and loss jumps in RNN training","created":"2023-10-26","cited_by_count":17},{"id":"2410.09385","title":"Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models","created":"2024-10-12","cited_by_count":17},{"id":"1512.05702","title":"Synthesis of recurrent neural networks for dynamical system simulation","created":"2015-12-17","cited_by_count":16},{"id":"2111.02922","title":"Reconstructing Nonlinear Dynamical Systems from Multi-Modal Time Series","created":"2021-11-04","cited_by_count":16},{"id":"2406.16749","title":"Inferring stochastic low-rank recurrent neural networks from neural data","created":"2024-06-24","cited_by_count":15},{"id":"2410.04814","title":"Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data","created":"2024-10-07","cited_by_count":15},{"id":"2210.01407","title":"Homotopy-based training of NeuralODEs for accurate dynamics discovery","created":"2022-10-04","cited_by_count":14},{"id":"2212.07892","title":"Integrating Multimodal Data for Joint Generative Modeling of Complex Dynamics","created":"2022-12-15","cited_by_count":14},{"id":"1511.03771","title":"Improving performance of recurrent neural network with relu nonlinearity","created":"2015-11-12","cited_by_count":12},{"id":"2502.12944","title":"Performance of Zero-Shot Time Series Foundation Models on Cloud Data","created":"2025-02-18","cited_by_count":10},{"id":"2411.02949","title":"A scalable generative model for dynamical system reconstruction from neuroimaging data","created":"2024-11-05","cited_by_count":9},{"id":"1904.03026","title":"Inferring the dynamics of oscillatory systems using recurrent neural networks","created":"2019-04-04","cited_by_count":8},{"id":"2406.04934","title":"Optimal Recurrent Network Topologies for Dynamical Systems Reconstruction","created":"2024-06-07","cited_by_count":8},{"id":"2502.05335","title":"Towards Foundational Models for Dynamical System Reconstruction: Hierarchical Meta-Learning via Mixture of Experts","created":"2025-02-07","cited_by_count":5}],"next_cursor":null}