{"list":"other","total":55,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"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":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"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":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"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":"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":"2205.14415","title":"Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting","created":"2022-05-28","cited_by_count":391},{"id":"2105.06643","title":"Monash Time Series Forecasting Archive","created":"2021-05-14","cited_by_count":267},{"id":"2403.20150","title":"TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods","created":"2024-03-29","cited_by_count":249},{"id":"2402.02368","title":"Timer: Generative Pre-trained Transformers Are Large Time Series Models","created":"2024-02-04","cited_by_count":208},{"id":"2210.08964","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","created":"2022-09-20","cited_by_count":172},{"id":"2406.16964","title":"Are Language Models Actually Useful for Time Series Forecasting?","created":"2024-06-22","cited_by_count":168},{"id":"2202.01381","title":"ETSformer: Exponential Smoothing Transformers for Time-series Forecasting","created":"2022-02-03","cited_by_count":148},{"id":"2202.01575","title":"CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting","created":"2022-02-03","cited_by_count":144},{"id":"2401.03955","title":"Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series","created":"2024-01-08","cited_by_count":127},{"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":"2405.00946","title":"SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters","created":"2024-05-02","cited_by_count":107},{"id":"2304.05206","title":"The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting","created":"2023-04-11","cited_by_count":101},{"id":"2306.10125","title":"Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects","created":"2023-06-16","cited_by_count":99},{"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":"2305.10716","title":"A Survey on Time-Series Pre-Trained Models","created":"2023-05-18","cited_by_count":52},{"id":"1710.00886","title":"Classification of Time-Series Images Using Deep Convolutional Neural Networks","created":"2017-10-02","cited_by_count":38},{"id":"2310.14838","title":"Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift","created":"2023-10-23","cited_by_count":25},{"id":"2402.04852","title":"Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning","created":"2024-02-07","cited_by_count":25},{"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":"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":"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}