{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"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":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"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":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"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":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210},{"id":"1704.04110","title":"DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks","created":"2017-04-13","cited_by_count":1013},{"id":"1905.10437","title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","created":"2019-05-24","cited_by_count":753},{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"1907.00235","title":"Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting","created":"2019-06-29","cited_by_count":607},{"id":"2003.01332","title":"Heterogeneous Graph Transformer","created":"2020-03-03","cited_by_count":582},{"id":"2006.10637","title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","created":"2020-06-18","cited_by_count":530},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497},{"id":"2106.10466","title":"TS2Vec: Towards Universal Representation of Time Series","created":"2021-06-19","cited_by_count":471},{"id":"2004.13408","title":"Time Series Forecasting With Deep Learning: A Survey","created":"2020-04-28","cited_by_count":459},{"id":"2010.02803","title":"A Transformer-based Framework for Multivariate Time Series Representation Learning","created":"2020-10-06","cited_by_count":453},{"id":"1810.07758","title":"The UCR Time Series Archive","created":"2018-10-17","cited_by_count":431},{"id":"1811.00075","title":"The UEA multivariate time series classification archive, 2018","created":"2018-10-31","cited_by_count":338},{"id":"2103.07719","title":"Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting","created":"2021-03-13","cited_by_count":299},{"id":"1608.08242","title":"Temporal Convolutional Networks: A Unified Approach to Action Segmentation","created":"2016-08-29","cited_by_count":199},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186},{"id":"1612.08544","title":"Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data","created":"2016-12-27","cited_by_count":171},{"id":"2205.08897","title":"FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting","created":"2022-05-18","cited_by_count":147},{"id":"2310.08278","title":"Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting","created":"2023-10-12","cited_by_count":113},{"id":"2310.11829","title":"Graph Foundation Models: Concepts, Opportunities and Challenges","created":"2023-10-18","cited_by_count":103},{"id":"1412.1602","title":"End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results","created":"2014-12-04","cited_by_count":68},{"id":"2102.06828","title":"Domain Adaptation for Time Series Forecasting via Attention Sharing","created":"2021-02-13","cited_by_count":68},{"id":"2007.03113","title":"Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks","created":"2020-07-06","cited_by_count":64},{"id":"2301.08871","title":"Ti-MAE: Self-Supervised Masked Time Series Autoencoders","created":"2023-01-21","cited_by_count":63},{"id":"2204.13767","title":"Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting--Full Version","created":"2022-04-28","cited_by_count":59},{"id":"2305.16742","title":"Parameter-Efficient Fine-Tuning without Introducing New Latency","created":"2023-05-26","cited_by_count":59},{"id":"2002.12898","title":"PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecasting","created":"2020-02-10","cited_by_count":55},{"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":"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":"1603.09420","title":"Minimal Gated Unit for Recurrent Neural Networks","created":"2016-03-31","cited_by_count":40},{"id":"1807.00981","title":"Learning concise representations for regression by evolving networks of trees","created":"2018-07-03","cited_by_count":33},{"id":"1911.07893","title":"Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition","created":"2019-11-18","cited_by_count":24},{"id":"2005.03297","title":"Knowledge Enhanced Neural Fashion Trend Forecasting","created":"2020-05-07","cited_by_count":18},{"id":"2312.10868","title":"From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape","created":"2023-12-18","cited_by_count":18},{"id":"2305.14582","title":"Interpretation of Time-Series Deep Models: A Survey","created":"2023-05-23","cited_by_count":15},{"id":"2308.01578","title":"Unsupervised Representation Learning for Time Series: A Review","created":"2023-08-03","cited_by_count":14},{"id":"2201.07006","title":"Time Series Generation with Masked Autoencoder","created":"2022-01-14","cited_by_count":12},{"id":"2109.08381","title":"From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibaba","created":"2021-09-17","cited_by_count":10},{"id":"1911.11374","title":"Representation Learning: A Statistical Perspective","created":"2019-11-26","cited_by_count":7},{"id":"2103.01992","title":"Improving Neural Networks for Time Series Forecasting using Data Augmentation and AutoML","created":"2021-03-02","cited_by_count":7}],"next_cursor":null}