{"list":"other","total":68,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"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":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424},{"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":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2310.06625","title":"iTransformer: Inverted Transformers Are Effective for Time Series Forecasting","created":"2023-10-10","cited_by_count":931},{"id":"1905.10437","title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","created":"2019-05-24","cited_by_count":753},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"2010.02803","title":"A Transformer-based Framework for Multivariate Time Series Representation Learning","created":"2020-10-06","cited_by_count":453},{"id":"1802.04431","title":"Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding","created":"2018-02-13","cited_by_count":410},{"id":"2205.14415","title":"Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting","created":"2022-05-28","cited_by_count":391},{"id":"1811.00075","title":"The UEA multivariate time series classification archive, 2018","created":"2018-10-31","cited_by_count":338},{"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":"2403.20150","title":"TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods","created":"2024-03-29","cited_by_count":249},{"id":"2310.04948","title":"TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting","created":"2023-10-08","cited_by_count":174},{"id":"2210.08964","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","created":"2022-09-20","cited_by_count":172},{"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":"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":"2204.08770","title":"GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning","created":"2022-04-19","cited_by_count":128},{"id":"2305.15525","title":"Large Language Models are Few-Shot Health Learners","created":"2023-05-24","cited_by_count":118},{"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":"2412.10859","title":"DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting","created":"2024-12-14","cited_by_count":107},{"id":"2402.05956","title":"Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting","created":"2024-02-04","cited_by_count":104},{"id":"2406.01638","title":"TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment","created":"2024-06-03","cited_by_count":103},{"id":"2106.00515","title":"KVT: k-NN Attention for Boosting Vision Transformers","created":"2021-05-28","cited_by_count":65},{"id":"2402.02370","title":"AutoTimes: Autoregressive Time Series Forecasters via Large Language Models","created":"2024-02-04","cited_by_count":65},{"id":"1811.01533","title":"Transfer learning for time series classification","created":"2018-11-05","cited_by_count":60},{"id":"2311.06612","title":"PerceptionGPT: Effectively Fusing Visual Perception into LLM","created":"2023-11-11","cited_by_count":59},{"id":"2402.04059","title":"Deep Learning for Multivariate Time Series Imputation: A Survey","created":"2024-02-06","cited_by_count":57},{"id":"2203.10716","title":"Forecast Evaluation for Data Scientists: Common Pitfalls and Best Practices","created":"2022-03-21","cited_by_count":55},{"id":"2405.19363","title":"Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification","created":"2024-05-24","cited_by_count":53},{"id":"2510.23672","title":"DBLoss: Decomposition-based Loss Function for Time Series Forecasting","created":"2025-10-27","cited_by_count":45},{"id":"2201.04828","title":"Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecasting","created":"2022-01-13","cited_by_count":42},{"id":"2510.14510","title":"Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective","created":"2025-10-16","cited_by_count":39},{"id":"2304.07919","title":"Chain of Thought Prompt Tuning in Vision Language Models","created":"2023-04-16","cited_by_count":34},{"id":"2406.03751","title":"Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting","created":"2024-06-06","cited_by_count":34},{"id":"2402.04852","title":"Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning","created":"2024-02-07","cited_by_count":25},{"id":"2311.11413","title":"Large Pre-trained time series models for cross-domain Time series analysis tasks","created":"2023-11-19","cited_by_count":23},{"id":"2212.00724","title":"SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity Recognition","created":"2022-11-25","cited_by_count":21},{"id":"2410.23992","title":"Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting","created":"2024-10-31","cited_by_count":21},{"id":"2309.12028","title":"Dynamic Hypergraph Structure Learning for Traffic Flow Forecasting","created":"2023-09-21","cited_by_count":14},{"id":"2401.09261","title":"MSHyper: Multi-Scale Hypergraph Transformer for Long-Range Time Series Forecasting","created":"2024-01-17","cited_by_count":12},{"id":"2410.00049","title":"Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph","created":"2024-09-28","cited_by_count":10},{"id":"2112.07459","title":"Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting","created":"2021-12-14","cited_by_count":9},{"id":"2410.22631","title":"DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach","created":"2024-10-30","cited_by_count":3},{"id":"2408.00041","title":"Con4m: Context-aware Consistency Learning Framework for Segmented Time Series Classification","created":"2024-07-31","cited_by_count":2},{"id":"2509.02217","title":"ST-Hyper: Learning High-Order Dependencies Across Multiple Spatial-Temporal Scales for Multivariate Time Series Forecasting","created":"2025-09-02","cited_by_count":2}],"next_cursor":null}