{"list":"other","total":53,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"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":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210},{"id":"2210.02186","title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis","created":"2022-10-05","cited_by_count":1058},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"1703.07015","title":"Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks","created":"2017-03-21","cited_by_count":879},{"id":"1905.10437","title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","created":"2019-05-24","cited_by_count":753},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"1803.09050","title":"Learning to Reweight Examples for Robust Deep Learning","created":"2018-03-24","cited_by_count":675},{"id":"1606.00709","title":"f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization","created":"2016-06-02","cited_by_count":506},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"id":"2402.03885","title":"MOMENT: A Family of Open Time-series Foundation Models","created":"2024-02-06","cited_by_count":482},{"id":"2004.13408","title":"Time Series Forecasting With Deep Learning: A Survey","created":"2020-04-28","cited_by_count":459},{"id":"1908.01000","title":"InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization","created":"2019-07-31","cited_by_count":441},{"id":"1802.04431","title":"Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding","created":"2018-02-13","cited_by_count":410},{"id":"2110.02642","title":"Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy","created":"2021-10-06","cited_by_count":394},{"id":"2205.14415","title":"Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting","created":"2022-05-28","cited_by_count":391},{"id":"2405.14616","title":"TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting","created":"2024-05-23","cited_by_count":346},{"id":"1910.13051","title":"ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels","created":"2019-10-29","cited_by_count":339},{"id":"1811.00075","title":"The UEA multivariate time series classification archive, 2018","created":"2018-10-31","cited_by_count":338},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275},{"id":"1901.10738","title":"Unsupervised Scalable Representation Learning for Multivariate Time Series","created":"2019-01-30","cited_by_count":269},{"id":"2105.06643","title":"Monash Time Series Forecasting Archive","created":"2021-05-14","cited_by_count":267},{"id":"1703.01785","title":"Forward and Reverse Gradient-Based Hyperparameter Optimization","created":"2017-03-06","cited_by_count":234},{"id":"2410.10393","title":"GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation","created":"2024-10-14","cited_by_count":212},{"id":"2310.04948","title":"TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting","created":"2023-10-08","cited_by_count":174},{"id":"2210.08964","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","created":"2022-09-20","cited_by_count":172},{"id":"2311.06184","title":"Frequency-domain MLPs are More Effective Learners in Time Series Forecasting","created":"2023-11-10","cited_by_count":172},{"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":"2207.01186","title":"Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures","created":"2022-07-04","cited_by_count":160},{"id":"2202.01381","title":"ETSformer: Exponential Smoothing Transformers for Time-series Forecasting","created":"2022-02-03","cited_by_count":148},{"id":"2403.00131","title":"UniTS: A Unified Multi-Task Time Series Model","created":"2024-02-29","cited_by_count":94},{"id":"2405.10825","title":"Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities","created":"2024-05-17","cited_by_count":83},{"id":"2402.02370","title":"AutoTimes: Autoregressive Time Series Forecasters via Large Language Models","created":"2024-02-04","cited_by_count":65},{"id":"2402.03182","title":"Empowering Time Series Analysis with Large Language Models: A Survey","created":"2024-02-05","cited_by_count":60},{"id":"2002.09545","title":"RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks","created":"2020-02-21","cited_by_count":55},{"id":"1912.12179","title":"Locality and compositionality in zero-shot learning","created":"2019-12-20","cited_by_count":29},{"id":"2309.11600","title":"Importance-aware Co-teaching for Offline Model-based Optimization","created":"2023-09-20","cited_by_count":28},{"id":"2207.11719","title":"Gradient-based Bi-level Optimization for Deep Learning: A Survey","created":"2022-07-24","cited_by_count":26},{"id":"2310.04752","title":"A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization","created":"2023-10-07","cited_by_count":24},{"id":"2305.14690","title":"Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems","created":"2023-05-24","cited_by_count":9},{"id":"2303.06389","title":"Uncertainty-Aware Instance Reweighting for Off-Policy Learning","created":"2023-03-11","cited_by_count":3},{"id":"2206.00147","title":"Unbiased Implicit Feedback via Bi-level Optimization","created":"2022-05-31","cited_by_count":2}],"next_cursor":null}