{"list":"other","total":52,"rows":[{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"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":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"1609.04802","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","created":"2016-09-15","cited_by_count":1908},{"id":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2310.06625","title":"iTransformer: Inverted Transformers Are Effective for Time Series Forecasting","created":"2023-10-10","cited_by_count":931},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2402.02592","title":"Unified Training of Universal Time Series Forecasting Transformers","created":"2024-02-04","cited_by_count":614},{"id":"2402.03885","title":"MOMENT: A Family of Open Time-series Foundation Models","created":"2024-02-06","cited_by_count":482},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"1909.04939","title":"InceptionTime: Finding AlexNet for Time Series Classification","created":"2019-09-11","cited_by_count":387},{"id":"1611.06455","title":"Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline","created":"2016-11-20","cited_by_count":360},{"id":"2303.16203","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","created":"2023-03-28","cited_by_count":306},{"id":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302},{"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":"2410.10393","title":"GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation","created":"2024-10-14","cited_by_count":212},{"id":"2402.02368","title":"Timer: Generative Pre-trained Transformers Are Large Time Series Models","created":"2024-02-04","cited_by_count":208},{"id":"2307.03756","title":"FITS: Modeling Time Series with $10k$ Parameters","created":"2023-07-06","cited_by_count":195},{"id":"2510.15821","title":"Chronos-2: From Univariate to Universal Forecasting","created":"2025-10-17","cited_by_count":194},{"id":"2403.01742","title":"Diffusion-TS: Interpretable Diffusion for General Time Series Generation","created":"2024-03-04","cited_by_count":184},{"id":"2502.00816","title":"Sundial: A Family of Highly Capable Time Series Foundation Models","created":"2025-02-02","cited_by_count":180},{"id":"2111.08095","title":"TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation","created":"2021-11-15","cited_by_count":142},{"id":"2505.23719","title":"TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning","created":"2025-05-29","cited_by_count":120},{"id":"2403.00131","title":"UniTS: A Unified Multi-Task Time Series Model","created":"2024-02-29","cited_by_count":94},{"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":"2006.08571","title":"COT-GAN: Generating Sequential Data via Causal Optimal Transport","created":"2020-06-15","cited_by_count":71},{"id":"1302.2277","title":"A Time Series Forest for Classification and Feature Extraction","created":"2013-02-09","cited_by_count":69},{"id":"2505.14766","title":"This Time is Different: An Observability Perspective on Time Series Foundation Models","created":"2025-05-20","cited_by_count":68},{"id":"2303.04743","title":"Vector Quantized Time Series Generation with a Bidirectional Prior Model","created":"2023-03-08","cited_by_count":50},{"id":"2402.16412","title":"TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis","created":"2024-02-26","cited_by_count":39},{"id":"2508.02739","title":"Kronos: A Foundation Model for the Language of Financial Markets","created":"2025-08-02","cited_by_count":26},{"id":"2502.15637","title":"Mantis: Lightweight Foundation Model for Time Series Classification","created":"2025-02-21","cited_by_count":24},{"id":"2506.11029","title":"Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Model","created":"2025-05-20","cited_by_count":24},{"id":"2109.13514","title":"Random Dilated Shapelet Transform: A New Approach for Time Series Shapelets","created":"2021-09-28","cited_by_count":22},{"id":"2508.09191","title":"From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization","created":"2025-08-08","cited_by_count":13},{"id":"2411.01006","title":"Abstracted Shapes as Tokens -- A Generalizable and Interpretable Model for Time-series Classification","created":"2024-11-01","cited_by_count":12},{"id":"2502.12448","title":"From Principles to Applications: A Comprehensive Survey of Discrete Tokenizers in Generation, Comprehension, Recommendation, and Information Retrieval","created":"2025-02-18","cited_by_count":11},{"id":"2409.02869","title":"Look Into the LITE in Deep Learning for Time Series Classification","created":"2024-09-04","cited_by_count":9},{"id":"2510.21795","title":"Xihe: Scalable Zero-Shot Time Series Learner Via Hierarchical Interleaved Block Attention","created":"2025-10-20","cited_by_count":8},{"id":"2502.08302","title":"HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting","created":"2025-02-12","cited_by_count":7}],"next_cursor":null}