{"list":"other","total":56,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"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":"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":"1912.09363","title":"Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting","created":"2019-12-19","cited_by_count":761},{"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":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"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":"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":"2304.08424","title":"Long-term Forecasting with TiDE: Time-series Dense Encoder","created":"2023-04-17","cited_by_count":332},{"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":"2105.06643","title":"Monash Time Series Forecasting Archive","created":"2021-05-14","cited_by_count":267},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"1811.09751","title":"Characterizing and Avoiding Negative Transfer","created":"2018-11-24","cited_by_count":229},{"id":"2410.10393","title":"GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation","created":"2024-10-14","cited_by_count":212},{"id":"1711.11053","title":"A Multi-Horizon Quantile Recurrent Forecaster","created":"2017-11-29","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":"2310.09751","title":"UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting","created":"2023-10-15","cited_by_count":144},{"id":"2410.10469","title":"Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts","created":"2024-10-14","cited_by_count":95},{"id":"2301.02280","title":"Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training","created":"2023-01-05","cited_by_count":91},{"id":"2301.03028","title":"Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement","created":"2023-01-08","cited_by_count":90},{"id":"2408.17253","title":"VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters","created":"2024-08-30","cited_by_count":88},{"id":"1506.00327","title":"Imaging Time-Series to Improve Classification and Imputation","created":"2015-06-01","cited_by_count":85},{"id":"2303.12799","title":"Time Series as Images: Vision Transformer for Irregularly Sampled Time Series","created":"2023-03-01","cited_by_count":79},{"id":"2404.07177","title":"Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic","created":"2024-04-10","cited_by_count":77},{"id":"2404.18886","title":"A Survey on Diffusion Models for Time Series and Spatio-Temporal Data","created":"2024-04-29","cited_by_count":67},{"id":"2402.12501","title":"Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection","created":"2024-02-19","cited_by_count":48},{"id":"2410.19538","title":"Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series","created":"2024-10-25","cited_by_count":43},{"id":"1710.00886","title":"Classification of Time-Series Images Using Deep Convolutional Neural Networks","created":"2017-10-02","cited_by_count":38},{"id":"2111.06581","title":"Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting","created":"2021-11-12","cited_by_count":32},{"id":"2502.08869","title":"Harnessing Vision Models for Time Series Analysis: A Survey","created":"2025-02-13","cited_by_count":26},{"id":"2401.03006","title":"The Rise of Diffusion Models in Time-Series Forecasting","created":"2024-01-05","cited_by_count":25},{"id":"2503.13709","title":"Multi-modal Time Series Analysis: A Tutorial and Survey","created":"2025-03-17","cited_by_count":24},{"id":"1904.08064","title":"Forecasting with time series imaging","created":"2019-04-17","cited_by_count":22},{"id":"2301.10166","title":"Leveraging Vision-Language Models for Granular Market Change Prediction","created":"2023-01-17","cited_by_count":22},{"id":"2402.02475","title":"TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling","created":"2024-02-04","cited_by_count":20},{"id":"2503.11835","title":"How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook","created":"2025-03-14","cited_by_count":20},{"id":"2503.11411","title":"Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models","created":"2025-03-14","cited_by_count":15},{"id":"2011.09052","title":"Visual Time Series Forecasting: An Image-driven Approach","created":"2020-11-18","cited_by_count":13},{"id":"2402.07570","title":"Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction","created":"2024-02-12","cited_by_count":11},{"id":"2407.07311","title":"ViTime: Foundation Model for Time Series Forecasting Powered by Vision Intelligence","created":"2024-07-10","cited_by_count":11},{"id":"2505.24003","title":"Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting","created":"2025-05-29","cited_by_count":9},{"id":"1509.07481","title":"Spatially Encoding Temporal Correlations to Classify Temporal Data Using Convolutional Neural Networks","created":"2015-09-24","cited_by_count":8},{"id":"2402.00607","title":"Are Synthetic Time-series Data Really not as Good as Real Data?","created":"2024-02-01","cited_by_count":7}],"next_cursor":null}