{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"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":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"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":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"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":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2406.06484","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","created":"2024-06-10","cited_by_count":396},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354},{"id":"1811.00075","title":"The UEA multivariate time series classification archive, 2018","created":"2018-10-31","cited_by_count":338},{"id":"2106.09305","title":"SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction","created":"2021-06-17","cited_by_count":338},{"id":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"1704.02971","title":"A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction","created":"2017-04-07","cited_by_count":245},{"id":"2403.14735","title":"Foundation Models for Time Series Analysis: A Tutorial and Survey","created":"2024-03-21","cited_by_count":239},{"id":"2410.10393","title":"GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation","created":"2024-10-14","cited_by_count":212},{"id":"2402.02368","title":"Timer: Generative Pre-trained Transformers Are Large Time Series Models","created":"2024-02-04","cited_by_count":208},{"id":"2406.07887","title":"An Empirical Study of Mamba-based Language Models","created":"2024-06-12","cited_by_count":186},{"id":"2502.00816","title":"Sundial: A Family of Highly Capable Time Series Foundation Models","created":"2025-02-02","cited_by_count":180},{"id":"1909.00590","title":"Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions","created":"2019-09-02","cited_by_count":172},{"id":"2406.16964","title":"Are Language Models Actually Useful for Time Series Forecasting?","created":"2024-06-22","cited_by_count":168},{"id":"2310.03589","title":"TimeGPT-1","created":"2023-10-05","cited_by_count":158},{"id":"2308.08469","title":"LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters","created":"2023-08-16","cited_by_count":129},{"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":"2405.16712","title":"Zamba: A Compact 7B SSM Hybrid Model","created":"2024-05-26","cited_by_count":124},{"id":"2505.23719","title":"TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning","created":"2025-05-29","cited_by_count":120},{"id":"2410.04803","title":"Timer-XL: Long-Context Transformers for Unified Time Series Forecasting","created":"2024-10-07","cited_by_count":87},{"id":"2502.10297","title":"DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products","created":"2025-02-14","cited_by_count":75},{"id":"2505.14766","title":"This Time is Different: An Observability Perspective on Time Series Foundation Models","created":"2025-05-20","cited_by_count":68},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62},{"id":"1906.05264","title":"GluonTS: Probabilistic Time Series Models in Python","created":"2019-06-12","cited_by_count":46},{"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":"2310.18780","title":"Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions","created":"2023-10-28","cited_by_count":24},{"id":"2506.11029","title":"Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Model","created":"2025-05-20","cited_by_count":24},{"id":"2504.04011","title":"Foundation Models for Time Series: A Survey","created":"2025-04-05","cited_by_count":23},{"id":"1901.00069","title":"Recurrent Neural Networks for Time Series Forecasting","created":"2019-01-01","cited_by_count":19},{"id":"2410.09385","title":"Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models","created":"2024-10-12","cited_by_count":17},{"id":"2510.25502","title":"TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting","created":"2025-10-29","cited_by_count":17},{"id":"2602.06909","title":"Revisiting the Generic Transformer: Deconstructing a Strong Baseline for Time Series Foundation Models","created":"2026-02-06","cited_by_count":12},{"id":"1709.03159","title":"R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecasting","created":"2017-09-10","cited_by_count":10},{"id":"2411.02941","title":"A Mamba Foundation Model for Time Series Forecasting","created":"2024-11-05","cited_by_count":9},{"id":"2509.25826","title":"Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models","created":"2025-09-30","cited_by_count":9},{"id":"2510.26777","title":"Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification","created":"2025-10-30","cited_by_count":9},{"id":"2503.07674","title":"TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variation","created":"2025-03-10","cited_by_count":8},{"id":"2510.21795","title":"Xihe: Scalable Zero-Shot Time Series Learner Via Hierarchical Interleaved Block Attention","created":"2025-10-20","cited_by_count":8},{"id":"2509.02844","title":"Conformal Prediction for Time-series Forecasting with Change Points","created":"2025-09-02","cited_by_count":5},{"id":"2509.15105","title":"Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting","created":"2025-09-18","cited_by_count":2}],"next_cursor":null}