{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"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":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2106.13008","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","created":"2021-06-24","cited_by_count":1676},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424},{"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":"1704.04110","title":"DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks","created":"2017-04-13","cited_by_count":1013},{"id":"2310.06625","title":"iTransformer: Inverted Transformers Are Effective for Time Series Forecasting","created":"2023-10-10","cited_by_count":931},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763},{"id":"1912.09363","title":"Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting","created":"2019-12-19","cited_by_count":761},{"id":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759},{"id":"1905.10437","title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","created":"2019-05-24","cited_by_count":753},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"2310.10688","title":"A decoder-only foundation model for time-series forecasting","created":"2023-10-14","cited_by_count":692},{"id":"1905.03197","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","created":"2019-05-08","cited_by_count":670},{"id":"2402.02592","title":"Unified Training of Universal Time Series Forecasting Transformers","created":"2024-02-04","cited_by_count":614},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497},{"id":"2402.03885","title":"MOMENT: A Family of Open Time-series Foundation Models","created":"2024-02-06","cited_by_count":482},{"id":"2106.10466","title":"TS2Vec: Towards Universal Representation of Time Series","created":"2021-06-19","cited_by_count":471},{"id":"2010.02803","title":"A Transformer-based Framework for Multivariate Time Series Representation Learning","created":"2020-10-06","cited_by_count":453},{"id":"2405.14616","title":"TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting","created":"2024-05-23","cited_by_count":346},{"id":"1610.00081","title":"Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction","created":"2016-10-01","cited_by_count":333},{"id":"2304.08424","title":"Long-term Forecasting with TiDE: Time-series Dense Encoder","created":"2023-04-17","cited_by_count":332},{"id":"2002.00469","title":"WeatherBench: A benchmark dataset for data-driven weather forecasting","created":"2020-02-02","cited_by_count":275},{"id":"2105.06643","title":"Monash Time Series Forecasting Archive","created":"2021-05-14","cited_by_count":267},{"id":"2206.08496","title":"Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency","created":"2022-06-17","cited_by_count":250},{"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":"1905.03806","title":"Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting","created":"2019-05-09","cited_by_count":161},{"id":"2310.03589","title":"TimeGPT-1","created":"2023-10-05","cited_by_count":158},{"id":"2209.06640","title":"Revisiting Neural Scaling Laws in Language and Vision","created":"2022-09-13","cited_by_count":132},{"id":"2306.08259","title":"LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting","created":"2023-06-14","cited_by_count":118},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110},{"id":"2405.00946","title":"SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters","created":"2024-05-02","cited_by_count":107},{"id":"2402.05956","title":"Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting","created":"2024-02-04","cited_by_count":104},{"id":"2306.10347","title":"DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection","created":"2023-06-17","cited_by_count":103},{"id":"2306.10125","title":"Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects","created":"2023-06-16","cited_by_count":99},{"id":"2406.11903","title":"A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges","created":"2024-06-15","cited_by_count":90},{"id":"2202.08408","title":"Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs","created":"2022-02-17","cited_by_count":72},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63},{"id":"2402.04059","title":"Deep Learning for Multivariate Time Series Imputation: A Survey","created":"2024-02-06","cited_by_count":57},{"id":"2305.12095","title":"CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting","created":"2023-05-20","cited_by_count":55},{"id":"2307.01909","title":"ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling","created":"2023-07-04","cited_by_count":47},{"id":"2402.02713","title":"Position: What Can Large Language Models Tell Us about Time Series Analysis","created":"2024-02-05","cited_by_count":47},{"id":"2006.00630","title":"A machine learning approach for forecasting hierarchical time series","created":"2020-05-31","cited_by_count":29},{"id":"2312.06786","title":"Mixture-of-Linear-Experts for Long-term Time Series Forecasting","created":"2023-12-11","cited_by_count":29},{"id":"2307.00142","title":"BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting","created":"2023-06-30","cited_by_count":26},{"id":"2310.05063","title":"Pushing the Limits of Pre-training for Time Series Forecasting in the CloudOps Domain","created":"2023-10-08","cited_by_count":23},{"id":"2109.10399","title":"SubseasonalClimateUSA: A Dataset for Subseasonal Forecasting and Benchmarking","created":"2021-09-21","cited_by_count":21},{"id":"2208.04360","title":"SDWPF: A Dataset for Spatial Dynamic Wind Power Forecasting Challenge at KDD Cup 2022","created":"2022-08-08","cited_by_count":21},{"id":"2405.10800","title":"Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting","created":"2024-05-17","cited_by_count":18},{"id":"2206.02107","title":"Interpretable Mixture of Experts","created":"2022-06-05","cited_by_count":17},{"id":"2402.11463","title":"Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective","created":"2024-02-18","cited_by_count":17},{"id":"1906.03751","title":"RobustTrend: A Huber Loss with a Combined First and Second Order Difference Regularization for Time Series Trend Filtering","created":"2019-06-10","cited_by_count":12},{"id":"2305.00706","title":"Full Scaling Automation for Sustainable Development of Green Data Centers","created":"2023-05-01","cited_by_count":5},{"id":"2408.13960","title":"Time Series Analysis for Education: Methods, Applications, and Future Directions","created":"2024-08-25","cited_by_count":5},{"id":"2212.13706","title":"End-to-End Modeling Hierarchical Time Series Using Autoregressive Transformer and Conditional Normalizing Flow based Reconciliation","created":"2022-12-28","cited_by_count":4}],"next_cursor":null}