{"list":"other","total":54,"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"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":"2106.13008","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","created":"2021-06-24","cited_by_count":1676},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210},{"id":"1906.00121","title":"Graph WaveNet for Deep Spatial-Temporal Graph Modeling","created":"2019-05-31","cited_by_count":829},{"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":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632},{"id":"2005.11650","title":"Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks","created":"2020-05-24","cited_by_count":566},{"id":"1905.00067","title":"MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing","created":"2019-04-30","cited_by_count":443},{"id":"1911.08415","title":"GMAN: A Graph Multi-Attention Network for Traffic Prediction","created":"2019-11-11","cited_by_count":434},{"id":"2403.14735","title":"Foundation Models for Time Series Analysis: A Tutorial and Survey","created":"2024-03-21","cited_by_count":239},{"id":"2106.12931","title":"Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting","created":"2021-06-24","cited_by_count":210},{"id":"2210.08964","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","created":"2022-09-20","cited_by_count":172},{"id":"2101.06861","title":"Discrete Graph Structure Learning for Forecasting Multiple Time Series","created":"2021-01-18","cited_by_count":171},{"id":"1910.03002","title":"High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes","created":"2019-10-07","cited_by_count":148},{"id":"2202.01381","title":"ETSformer: Exponential Smoothing Transformers for Time-series Forecasting","created":"2022-02-03","cited_by_count":148},{"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":"2004.10240","title":"Deep Learning for Time Series Forecasting: Tutorial and Literature Survey","created":"2020-04-21","cited_by_count":117},{"id":"2206.09113","title":"Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting","created":"2022-06-18","cited_by_count":117},{"id":"2310.08278","title":"Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting","created":"2023-10-12","cited_by_count":113},{"id":"2206.12839","title":"Repository-Level Prompt Generation for Large Language Models of Code","created":"2022-06-26","cited_by_count":106},{"id":"2311.01933","title":"ForecastPFN: Synthetically-Trained Zero-Shot Forecasting","created":"2023-11-03","cited_by_count":104},{"id":"2405.20304","title":"Group Robust Preference Optimization in Reward-free RLHF","created":"2024-05-30","cited_by_count":95},{"id":"2402.11838","title":"UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction","created":"2024-02-19","cited_by_count":87},{"id":"2311.12399","title":"A Survey of Graph Meets Large Language Model: Progress and Future Directions","created":"2023-11-21","cited_by_count":85},{"id":"2401.10134","title":"Spatial-Temporal Large Language Model for Traffic Prediction","created":"2024-01-18","cited_by_count":83},{"id":"2403.00813","title":"UrbanGPT: Spatio-Temporal Large Language Models","created":"2024-02-25","cited_by_count":81},{"id":"2306.13089","title":"GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning","created":"2023-05-28","cited_by_count":70},{"id":"1907.06051","title":"k-hop Graph Neural Networks","created":"2019-07-13","cited_by_count":57},{"id":"2310.01668","title":"Locality-Aware Graph-Rewiring in GNNs","created":"2023-10-02","cited_by_count":56},{"id":"2105.07536","title":"Theoretical Foundations of t-SNE for Visualizing High-Dimensional Clustered Data","created":"2021-05-16","cited_by_count":55},{"id":"1812.01767","title":"RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series","created":"2018-12-05","cited_by_count":54},{"id":"2304.04052","title":"Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder","created":"2023-04-08","cited_by_count":44},{"id":"2310.05140","title":"Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements","created":"2023-10-08","cited_by_count":42},{"id":"2310.20496","title":"BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis","created":"2023-10-31","cited_by_count":41},{"id":"2310.01327","title":"TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series","created":"2023-10-02","cited_by_count":26},{"id":"2405.17898","title":"FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction","created":"2024-05-28","cited_by_count":18},{"id":"1901.10651","title":"Geometric structure of graph Laplacian embeddings","created":"2019-01-30","cited_by_count":10},{"id":"2302.09292","title":"FrAug: Frequency Domain Augmentation for Time Series Forecasting","created":"2023-02-18","cited_by_count":8},{"id":"2404.03380","title":"On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers","created":"2024-04-04","cited_by_count":8},{"id":"2406.06399","title":"Should We Fine-Tune or RAG? Evaluating Different Techniques to Adapt LLMs for Dialogue","created":"2024-06-10","cited_by_count":7},{"id":"1701.05638","title":"Objective priors for the number of degrees of freedom of a multivariate t distribution and the t-copula","created":"2017-01-19","cited_by_count":4}],"next_cursor":null}