{"list":"other","total":122,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1611.07308","title":"Variational Graph Auto-Encoders","created":"2016-11-21","cited_by_count":1382},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1709.04875","title":"Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting","created":"2017-09-14","cited_by_count":1136},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"2306.08302","title":"Unifying Large Language Models and Knowledge Graphs: A Roadmap","created":"2023-06-14","cited_by_count":668},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632},{"id":"2107.03502","title":"CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation","created":"2021-07-07","cited_by_count":582},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"1807.06653","title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","created":"2018-07-17","cited_by_count":455},{"id":"1908.01000","title":"InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization","created":"2019-07-31","cited_by_count":441},{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1610.00081","title":"Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction","created":"2016-10-01","cited_by_count":333},{"id":"1909.03193","title":"KG-BERT: BERT for Knowledge Graph Completion","created":"2019-09-07","cited_by_count":324},{"id":"2002.00469","title":"WeatherBench: A benchmark dataset for data-driven weather forecasting","created":"2020-02-02","cited_by_count":275},{"id":"1904.03436","title":"Unsupervised Embedding Learning via Invariant and Spreading Instance Feature","created":"2019-04-06","cited_by_count":232},{"id":"1704.03165","title":"struc2vec: Learning Node Representations from Structural Identity","created":"2017-04-11","cited_by_count":215},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194},{"id":"2011.09980","title":"Geography-Aware Self-Supervised Learning","created":"2020-11-19","cited_by_count":190},{"id":"1712.06080","title":"Spatial As Deep: Spatial CNN for Traffic Scene Understanding","created":"2017-12-17","cited_by_count":187},{"id":"2001.02908","title":"Spatial-Temporal Transformer Networks for Traffic Flow Forecasting","created":"2020-01-09","cited_by_count":180},{"id":"2310.04948","title":"TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting","created":"2023-10-08","cited_by_count":174},{"id":"1906.04928","title":"Deep Learning for Spatio-Temporal Data Mining: A Survey","created":"2019-06-11","cited_by_count":172},{"id":"2210.08964","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","created":"2022-09-20","cited_by_count":172},{"id":"2211.02556","title":"Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast","created":"2022-11-03","cited_by_count":166},{"id":"2303.14483","title":"Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey","created":"2023-03-25","cited_by_count":140},{"id":"2301.07945","title":"PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction","created":"2023-01-19","cited_by_count":137},{"id":"2112.03558","title":"Graph Neural Controlled Differential Equations for Traffic Forecasting","created":"2021-12-07","cited_by_count":133},{"id":"2201.05337","title":"A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models","created":"2022-01-14","cited_by_count":129},{"id":"1703.08581","title":"Sequence-to-Sequence Models Can Directly Translate Foreign Speech","created":"2017-03-24","cited_by_count":121},{"id":"2206.09113","title":"Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting","created":"2022-06-18","cited_by_count":117},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110},{"id":"2404.11912","title":"TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding","created":"2024-04-18","cited_by_count":102},{"id":"1905.04722","title":"Learning Phase Competition for Traffic Signal Control","created":"2019-05-12","cited_by_count":87},{"id":"2402.11838","title":"UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction","created":"2024-02-19","cited_by_count":87},{"id":"2401.10134","title":"Spatial-Temporal Large Language Model for Traffic Prediction","created":"2024-01-18","cited_by_count":83},{"id":"2301.13629","title":"DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Models","created":"2023-01-31","cited_by_count":81},{"id":"2212.04475","title":"Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction","created":"2022-12-07","cited_by_count":77},{"id":"2306.11025","title":"Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting","created":"2023-06-19","cited_by_count":77},{"id":"2305.00624","title":"Diffusion Models for Time Series Applications: A Survey","created":"2023-05-01","cited_by_count":72},{"id":"2105.04100","title":"Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting","created":"2021-05-10","cited_by_count":67},{"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":"2009.14168","title":"Self-Supervised Few-Shot Learning on Point Clouds","created":"2020-09-29","cited_by_count":66},{"id":"2304.11582","title":"DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model","created":"2023-04-23","cited_by_count":65},{"id":"2112.01514","title":"Self-supervised Video Transformer","created":"2021-12-02","cited_by_count":64},{"id":"2005.11437","title":"S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation","created":"2020-05-23","cited_by_count":63},{"id":"2204.04216","title":"Learning Trajectory-Aware Transformer for Video Super-Resolution","created":"2022-04-08","cited_by_count":61},{"id":"2211.09510","title":"Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics","created":"2022-11-17","cited_by_count":58},{"id":"2303.04741","title":"GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation","created":"2023-03-03","cited_by_count":58},{"id":"2305.11421","title":"PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction","created":"2023-05-19","cited_by_count":44},{"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":"2404.17591","title":"Large Language Models for Next Point-of-Interest Recommendation","created":"2024-04-19","cited_by_count":40},{"id":"2003.01604","title":"Self-Supervised Graph Representation Learning via Global Context Prediction","created":"2020-03-03","cited_by_count":38},{"id":"2108.11873","title":"When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting?","created":"2021-08-26","cited_by_count":36},{"id":"2003.06167","title":"Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection","created":"2020-03-13","cited_by_count":35},{"id":"1811.03879","title":"Cross and Learn: Cross-Modal Self-Supervision","created":"2018-11-09","cited_by_count":34},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34},{"id":"1905.00149","title":"Self-Supervised Convolutional Subspace Clustering Network","created":"2019-05-01","cited_by_count":32},{"id":"2201.02435","title":"Spatial-Temporal Sequential Hypergraph Network for Crime Prediction with Dynamic Multiplex Relation Learning","created":"2022-01-07","cited_by_count":32},{"id":"2201.09760","title":"Multi-Graph Fusion Networks for Urban Region Embedding","created":"2022-01-24","cited_by_count":32},{"id":"1711.04710","title":"Spatio-Temporal Data Mining: A Survey of Problems and Methods","created":"2017-11-13","cited_by_count":29},{"id":"2304.08754","title":"W-MAE: Pre-trained weather model with masked autoencoder for multi-variable weather forecasting","created":"2023-04-18","cited_by_count":29},{"id":"2402.07369","title":"Diff-RNTraj: A Structure-aware Diffusion Model for Road Network-constrained Trajectory Generation","created":"2024-02-12","cited_by_count":29},{"id":"1811.06964","title":"Grasp2Vec: Learning Object Representations from Self-Supervised Grasping","created":"2018-11-16","cited_by_count":27},{"id":"2011.11004","title":"AST-GCN: Attribute-Augmented Spatiotemporal Graph Convolutional Network for Traffic Forecasting","created":"2020-11-22","cited_by_count":27},{"id":"2304.07041","title":"A Diffusion model for POI recommendation","created":"2023-04-14","cited_by_count":24},{"id":"2305.03920","title":"Automated Spatio-Temporal Graph Contrastive Learning","created":"2023-05-06","cited_by_count":24},{"id":"2303.16235","title":"Spatiotemporal Self-supervised Learning for Point Clouds in the Wild","created":"2023-03-28","cited_by_count":23},{"id":"2305.08381","title":"Parameter-efficient Tuning of Large-scale Multimodal Foundation Model","created":"2023-05-15","cited_by_count":23},{"id":"2403.02221","title":"TPLLM: A Traffic Prediction Framework Based on Pretrained Large Language Models","created":"2024-03-04","cited_by_count":23},{"id":"2310.17360","title":"Towards Unifying Diffusion Models for Probabilistic Spatio-Temporal Graph Learning","created":"2023-10-26","cited_by_count":20},{"id":"1810.03043","title":"Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning","created":"2018-10-06","cited_by_count":19},{"id":"2309.10547","title":"Towards Generative Modeling of Urban Flow through Knowledge-enhanced Denoising Diffusion","created":"2023-09-19","cited_by_count":17}],"next_cursor":"100"}