{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"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":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"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":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1703.07015","title":"Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks","created":"2017-03-21","cited_by_count":879},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"1809.04356","title":"Deep learning for time series classification: a review","created":"2018-09-12","cited_by_count":576},{"id":"1602.07868","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","created":"2016-02-25","cited_by_count":543},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"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":"2106.14112","title":"Time-Series Representation Learning via Temporal and Contextual Contrasting","created":"2021-06-26","cited_by_count":345},{"id":"1910.13051","title":"ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels","created":"2019-10-29","cited_by_count":339},{"id":"1811.00075","title":"The UEA multivariate time series classification archive, 2018","created":"2018-10-31","cited_by_count":338},{"id":"2310.08319","title":"Fine-Tuning LLaMA for Multi-Stage Text Retrieval","created":"2023-10-12","cited_by_count":272},{"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":"2106.00750","title":"Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding","created":"2021-06-01","cited_by_count":224},{"id":"1707.04585","title":"The Reversible Residual Network: Backpropagation Without Storing Activations","created":"2017-07-14","cited_by_count":217},{"id":"2308.08241","title":"TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series","created":"2023-08-16","cited_by_count":169},{"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":"2310.10436","title":"EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities","created":"2023-10-16","cited_by_count":154},{"id":"2402.01801","title":"Large Language Models for Time Series: A Survey","created":"2024-02-02","cited_by_count":114},{"id":"2106.09296","title":"Voice2Series: Reprogramming Acoustic Models for Time Series Classification","created":"2021-06-17","cited_by_count":91},{"id":"2404.11757","title":"Language Models Still Struggle to Zero-shot Reason about Time Series","created":"2024-04-17","cited_by_count":88},{"id":"2305.14201","title":"Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks","created":"2023-05-23","cited_by_count":84},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81},{"id":"1606.04130","title":"Modeling Missing Data in Clinical Time Series with RNNs","created":"2016-06-13","cited_by_count":80},{"id":"2303.12799","title":"Time Series as Images: Vision Transformer for Irregularly Sampled Time Series","created":"2023-03-01","cited_by_count":79},{"id":"2012.15832","title":"Shortformer: Better Language Modeling using Shorter Inputs","created":"2020-12-31","cited_by_count":76},{"id":"2202.06258","title":"Flowformer: Linearizing Transformers with Conservation Flows","created":"2022-02-13","cited_by_count":69},{"id":"2402.03182","title":"Empowering Time Series Analysis with Large Language Models: A Survey","created":"2024-02-05","cited_by_count":60},{"id":"2402.16132","title":"LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting","created":"2024-02-25","cited_by_count":59},{"id":"1806.04509","title":"A review on distance based time series classification","created":"2018-06-12","cited_by_count":40},{"id":"1909.09702","title":"Using Clinical Notes with Time Series Data for ICU Management","created":"2019-09-12","cited_by_count":38},{"id":"2404.16563","title":"Evaluating Large Language Models on Time Series Feature Understanding: A Comprehensive Taxonomy and Benchmark","created":"2024-04-25","cited_by_count":38},{"id":"1803.07427","title":"Multimodal Sentiment Analysis: Addressing Key Issues and Setting up the Baselines","created":"2018-03-19","cited_by_count":23},{"id":"2110.01839","title":"Truth-Conditional Captioning of Time Series Data","created":"2021-10-05","cited_by_count":11}],"next_cursor":null}