{"list":"other","total":127,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"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":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"1704.04110","title":"DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks","created":"2017-04-13","cited_by_count":1013},{"id":"2310.06625","title":"iTransformer: Inverted Transformers Are Effective for Time Series Forecasting","created":"2023-10-10","cited_by_count":931},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"1703.07015","title":"Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks","created":"2017-03-21","cited_by_count":879},{"id":"2202.11214","title":"FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators","created":"2022-02-22","cited_by_count":776},{"id":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759},{"id":"1905.10437","title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","created":"2019-05-24","cited_by_count":753},{"id":"2310.10688","title":"A decoder-only foundation model for time-series forecasting","created":"2023-10-14","cited_by_count":692},{"id":"2402.02592","title":"Unified Training of Universal Time Series Forecasting Transformers","created":"2024-02-04","cited_by_count":614},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"id":"2402.03885","title":"MOMENT: A Family of Open Time-series Foundation Models","created":"2024-02-06","cited_by_count":482},{"id":"1810.07758","title":"The UCR Time Series Archive","created":"2018-10-17","cited_by_count":431},{"id":"2003.06505","title":"AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data","created":"2020-03-13","cited_by_count":383},{"id":"1811.00075","title":"The UEA multivariate time series classification archive, 2018","created":"2018-10-31","cited_by_count":338},{"id":"2403.14735","title":"Foundation Models for Time Series Analysis: A Tutorial and Survey","created":"2024-03-21","cited_by_count":239},{"id":"2410.10393","title":"GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation","created":"2024-10-14","cited_by_count":212},{"id":"1905.03806","title":"Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting","created":"2019-05-09","cited_by_count":161},{"id":"2310.03589","title":"TimeGPT-1","created":"2023-10-05","cited_by_count":158},{"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":"2311.01933","title":"ForecastPFN: Synthetically-Trained Zero-Shot Forecasting","created":"2023-11-03","cited_by_count":104},{"id":"2306.10347","title":"DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection","created":"2023-06-17","cited_by_count":103},{"id":"2412.11376","title":"ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data","created":"2024-12-16","cited_by_count":100},{"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":"2403.00131","title":"UniTS: A Unified Multi-Task Time Series Model","created":"2024-02-29","cited_by_count":94},{"id":"2410.18959","title":"Context is Key: A Benchmark for Forecasting with Essential Textual Information","created":"2024-10-24","cited_by_count":87},{"id":"2002.02887","title":"Meta-learning framework with applications to zero-shot time-series forecasting","created":"2020-02-07","cited_by_count":70},{"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":"2509.26468","title":"fev-bench: A Realistic Benchmark for Time Series Forecasting","created":"2025-09-30","cited_by_count":64},{"id":"2411.08249","title":"Retrieval Augmented Time Series Forecasting","created":"2024-11-12","cited_by_count":46},{"id":"2402.10198","title":"SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention","created":"2024-02-15","cited_by_count":44},{"id":"2103.05632","title":"Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic Maps","created":"2021-03-09","cited_by_count":41},{"id":"2301.09152","title":"Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data","created":"2023-01-22","cited_by_count":40},{"id":"2503.07649","title":"TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster","created":"2025-03-06","cited_by_count":40},{"id":"2308.05566","title":"AutoGluon-TimeSeries: AutoML for Probabilistic Time Series Forecasting","created":"2023-08-10","cited_by_count":36},{"id":"2410.24087","title":"In-Context Fine-Tuning for Time-Series Foundation Models","created":"2024-10-31","cited_by_count":35},{"id":"2501.04970","title":"Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation","created":"2025-01-09","cited_by_count":35},{"id":"2502.16294","title":"TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data","created":"2025-02-22","cited_by_count":29},{"id":"2111.03753","title":"CloudRCA: A Root Cause Analysis Framework for Cloud Computing Platforms","created":"2021-11-05","cited_by_count":24},{"id":"2503.13709","title":"Multi-modal Time Series Analysis: A Tutorial and Survey","created":"2025-03-17","cited_by_count":24},{"id":"2503.12107","title":"ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables","created":"2025-03-15","cited_by_count":23},{"id":"2310.07402","title":"NuTime: Numerically Multi-Scaled Embedding for Large-Scale Time-Series Pretraining","created":"2023-10-11","cited_by_count":20},{"id":"2505.02138","title":"Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillation","created":"2025-05-04","cited_by_count":20},{"id":"2412.20810","title":"TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting","created":"2024-12-30","cited_by_count":17},{"id":"2510.25502","title":"TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting","created":"2025-10-29","cited_by_count":17},{"id":"2502.12920","title":"Lightweight Online Adaption for Time Series Foundation Model Forecasts","created":"2025-02-18","cited_by_count":16},{"id":"2502.10235","title":"AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting","created":"2025-02-14","cited_by_count":15},{"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":"2506.14087","title":"Multi-Scale Finetuning for Encoder-based Time Series Foundation Models","created":"2025-06-17","cited_by_count":14},{"id":"2412.08906","title":"Federated Foundation Models on Heterogeneous Time Series","created":"2024-12-12","cited_by_count":13},{"id":"2508.02879","title":"CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data","created":"2025-08-04","cited_by_count":13},{"id":"2505.18442","title":"Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting","created":"2025-05-24","cited_by_count":12},{"id":"2508.04379","title":"VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbones","created":"2025-08-06","cited_by_count":12},{"id":"2510.03519","title":"TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning","created":"2025-10-03","cited_by_count":12},{"id":"2601.12785","title":"Distilling Time Series Foundation Models for Efficient Forecasting","created":"2026-01-19","cited_by_count":11},{"id":"2409.11302","title":"Beyond LoRA: Exploring Efficient Fine-Tuning Techniques for Time Series Foundational Models","created":"2024-09-17","cited_by_count":10},{"id":"2502.21245","title":"TimesBERT: A BERT-Style Foundation Model for Time Series Understanding","created":"2025-02-28","cited_by_count":10},{"id":"2601.20280","title":"The Forecast After the Forecast: A Post-Processing Shift in Time Series","created":"2026-01-28","cited_by_count":10},{"id":"2510.03358","title":"Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility","created":"2025-10-02","cited_by_count":9},{"id":"2412.09880","title":"Financial Fine-tuning a Large Time Series Model","created":"2024-12-13","cited_by_count":8},{"id":"2506.22039","title":"UniCA: Unified Covariate Adaptation for Time Series Foundation Model","created":"2025-06-27","cited_by_count":7},{"id":"2510.16014","title":"STAR: Boosting Time Series Foundation Models for Anomaly Detection through State-aware Adapter","created":"2025-10-15","cited_by_count":7},{"id":"2511.05460","title":"Synapse: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Models","created":"2025-11-07","cited_by_count":7},{"id":"2603.21828","title":"CoRA: Boosting Time Series Foundation Models for Multivariate Forecasting through Correlation-aware Adapter","created":"2026-03-23","cited_by_count":7},{"id":"2103.08250","title":"Hierarchical forecasting with a top-down alignment of independent level forecasts","created":"2021-03-15","cited_by_count":6},{"id":"2410.03794","title":"Repurposing Foundation Model for Generalizable Medical Time Series Classification","created":"2024-10-03","cited_by_count":6},{"id":"2503.16991","title":"TRACE: Time SeRies PArameter EffiCient FinE-tuning","created":"2025-03-21","cited_by_count":6},{"id":"2507.08858","title":"Foundation models for time series forecasting: Application in conformal prediction","created":"2025-07-09","cited_by_count":6},{"id":"2510.12681","title":"CoRA: Covariate-Aware Adaptation of Time Series Foundation Models","created":"2025-10-14","cited_by_count":6},{"id":"2411.12824","title":"Generalized Prompt Tuning: Adapting Frozen Univariate Time Series Foundation Models for Multivariate Healthcare Time Series","created":"2024-11-19","cited_by_count":5},{"id":"2503.01936","title":"Decision-Focused Fine-Tuning of Time Series Foundation Models for Dispatchable Feeder Optimization","created":"2025-03-03","cited_by_count":5},{"id":"2601.00970","title":"Zero-shot Forecasting by Simulation Alone","created":"2026-01-02","cited_by_count":5},{"id":"2602.11550","title":"TS-Memory: Plug-and-Play Memory for Time Series Foundation Models","created":"2026-02-12","cited_by_count":5},{"id":"2509.18751","title":"Patch-based Memory Gate Model in Time Series Foundation Model","created":"2025-09-23","cited_by_count":4},{"id":"2510.02224","title":"Efficiently Generating Correlated Sample Paths from Multi-step Time Series Foundation Models","created":"2025-10-02","cited_by_count":4},{"id":"2603.14709","title":"Not All Retrievals are Useful: Cross-Attention for Input-Aware RAG in Time Series Forecasting","created":"2026-03-16","cited_by_count":4}],"next_cursor":"100"}