{"list":"other","total":58,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"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":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"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":"2210.02186","title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis","created":"2022-10-05","cited_by_count":1058},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"1704.04110","title":"DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks","created":"2017-04-13","cited_by_count":1013},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759},{"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":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2005.11650","title":"Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks","created":"2020-05-24","cited_by_count":566},{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"2402.03885","title":"MOMENT: A Family of Open Time-series Foundation Models","created":"2024-02-06","cited_by_count":482},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2304.08424","title":"Long-term Forecasting with TiDE: Time-series Dense Encoder","created":"2023-04-17","cited_by_count":332},{"id":"2103.07719","title":"Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting","created":"2021-03-13","cited_by_count":299},{"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":"1704.02971","title":"A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction","created":"2017-04-07","cited_by_count":245},{"id":"1909.06317","title":"A Comparative Study on Transformer vs RNN in Speech Applications","created":"2019-09-13","cited_by_count":211},{"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":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171},{"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":"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":"2310.03589","title":"TimeGPT-1","created":"2023-10-05","cited_by_count":158},{"id":"2310.09751","title":"UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting","created":"2023-10-15","cited_by_count":144},{"id":"2306.09364","title":"TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting","created":"2023-06-14","cited_by_count":139},{"id":"2402.00789","title":"Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces","created":"2024-02-01","cited_by_count":134},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131},{"id":"1703.04691","title":"Conditional Time Series Forecasting with Convolutional Neural Networks","created":"2017-03-14","cited_by_count":123},{"id":"2403.07300","title":"CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning","created":"2024-03-12","cited_by_count":108},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96},{"id":"2302.04501","title":"MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing","created":"2023-02-09","cited_by_count":53},{"id":"2212.10544","title":"Pretraining Without Attention","created":"2022-12-20","cited_by_count":51},{"id":"2302.14120","title":"Diagonal State Space Augmented Transformers for Speech Recognition","created":"2023-02-27","cited_by_count":25},{"id":"1303.2912","title":"Integrated Pre-Processing for Bayesian Nonlinear System Identification with Gaussian Processes","created":"2013-03-12","cited_by_count":8},{"id":"2305.14649","title":"A Joint Time-frequency Domain Transformer for Multivariate Time Series Forecasting","created":"2023-05-24","cited_by_count":5}],"next_cursor":null}