{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2211.14730","title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","created":"2022-11-27","cited_by_count":2039},{"id":"2106.13008","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","created":"2021-06-24","cited_by_count":1676},{"id":"1703.07015","title":"Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks","created":"2017-03-21","cited_by_count":879},{"id":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759},{"id":"2310.10688","title":"A decoder-only foundation model for time-series forecasting","created":"2023-10-14","cited_by_count":692},{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632},{"id":"2402.02592","title":"Unified Training of Universal Time Series Forecasting Transformers","created":"2024-02-04","cited_by_count":614},{"id":"2402.03885","title":"MOMENT: A Family of Open Time-series Foundation Models","created":"2024-02-06","cited_by_count":482},{"id":"1810.07758","title":"The UCR Time Series Archive","created":"2018-10-17","cited_by_count":431},{"id":"1802.04431","title":"Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding","created":"2018-02-13","cited_by_count":410},{"id":"2205.14415","title":"Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting","created":"2022-05-28","cited_by_count":391},{"id":"2302.09419","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","created":"2023-02-18","cited_by_count":368},{"id":"2409.16040","title":"Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts","created":"2024-09-24","cited_by_count":287},{"id":"2105.06643","title":"Monash Time Series Forecasting Archive","created":"2021-05-14","cited_by_count":267},{"id":"2403.14735","title":"Foundation Models for Time Series Analysis: A Tutorial and Survey","created":"2024-03-21","cited_by_count":239},{"id":"2402.02368","title":"Timer: Generative Pre-trained Transformers Are Large Time Series Models","created":"2024-02-04","cited_by_count":208},{"id":"1906.03950","title":"Domain-Specific Batch Normalization for Unsupervised Domain Adaptation","created":"2019-05-27","cited_by_count":197},{"id":"2407.13278","title":"Deep Time Series Models: A Comprehensive Survey and Benchmark","created":"2024-07-18","cited_by_count":197},{"id":"2502.00816","title":"Sundial: A Family of Highly Capable Time Series Foundation Models","created":"2025-02-02","cited_by_count":180},{"id":"2310.04948","title":"TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting","created":"2023-10-08","cited_by_count":174},{"id":"1702.08400","title":"Asymmetric Tri-training for Unsupervised Domain Adaptation","created":"2017-02-27","cited_by_count":152},{"id":"2108.04443","title":"AdaRNN: Adaptive Learning and Forecasting of Time Series","created":"2021-08-10","cited_by_count":121},{"id":"2302.00861","title":"SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling","created":"2023-02-02","cited_by_count":115},{"id":"2310.08278","title":"Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting","created":"2023-10-12","cited_by_count":113},{"id":"2302.14829","title":"Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecasting","created":"2023-02-22","cited_by_count":93},{"id":"2106.01899","title":"Adversarially Adaptive Normalization for Single Domain Generalization","created":"2021-06-01","cited_by_count":85},{"id":"2306.11025","title":"Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting","created":"2023-06-19","cited_by_count":77},{"id":"2404.08472","title":"TSLANet: Rethinking Transformers for Time Series Representation Learning","created":"2024-04-12","cited_by_count":74},{"id":"2301.08871","title":"Ti-MAE: Self-Supervised Masked Time Series Autoencoders","created":"2023-01-21","cited_by_count":63},{"id":"2302.03133","title":"Domain Adaptation for Time Series Under Feature and Label Shifts","created":"2023-02-06","cited_by_count":60},{"id":"2203.08321","title":"ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data","created":"2022-03-15","cited_by_count":45},{"id":"2208.06616","title":"Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification","created":"2022-08-13","cited_by_count":39},{"id":"2312.16427","title":"Learning to Embed Time Series Patches Independently","created":"2023-12-27","cited_by_count":35},{"id":"2405.17478","title":"Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer","created":"2024-05-24","cited_by_count":32},{"id":"2310.03916","title":"Toward a Foundation Model for Time Series Data","created":"2023-10-05","cited_by_count":28},{"id":"2412.05244","title":"Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization","created":"2024-12-06","cited_by_count":27},{"id":"2106.05956","title":"Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning","created":"2021-06-10","cited_by_count":25},{"id":"2310.14838","title":"Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift","created":"2023-10-23","cited_by_count":25},{"id":"2204.03342","title":"Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift","created":"2022-04-07","cited_by_count":24},{"id":"2308.02282","title":"DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization","created":"2023-08-04","cited_by_count":24},{"id":"2402.02475","title":"TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling","created":"2024-02-04","cited_by_count":20},{"id":"2003.00598","title":"Data Normalization for Bilinear Structures in High-Frequency Financial Time-series","created":"2020-03-01","cited_by_count":16},{"id":"2406.02635","title":"Evidentially Calibrated Source-Free Time-Series Domain Adaptation with Temporal Imputation","created":"2024-06-04","cited_by_count":6},{"id":"2405.10597","title":"UniCL: A Universal Contrastive Learning Framework for Large Time Series Models","created":"2024-05-17","cited_by_count":5},{"id":"2310.14720","title":"Extended Deep Adaptive Input Normalization for Preprocessing Time Series Data for Neural Networks","created":"2023-10-23","cited_by_count":2}],"next_cursor":null}