{"list":"other","total":121,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"1906.00121","title":"Graph WaveNet for Deep Spatial-Temporal Graph Modeling","created":"2019-05-31","cited_by_count":829},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632},{"id":"2205.10803","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","created":"2022-05-22","cited_by_count":448},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408},{"id":"1907.09693","title":"A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection","created":"2019-07-23","cited_by_count":374},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"2010.10144","title":"Keystroke Dynamics as Part of Lifelogging","created":"2020-10-20","cited_by_count":334},{"id":"1610.00081","title":"Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction","created":"2016-10-01","cited_by_count":333},{"id":"2311.15826","title":"GeoChat: Grounded Large Vision-Language Model for Remote Sensing","created":"2023-11-24","cited_by_count":328},{"id":"2212.14532","title":"Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning","created":"2022-12-30","cited_by_count":308},{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297},{"id":"2310.02601","title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control","created":"2023-10-04","cited_by_count":252},{"id":"1511.05298","title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs","created":"2015-11-17","cited_by_count":234},{"id":"2009.12547","title":"Causal Intervention for Weakly-Supervised Semantic Segmentation","created":"2020-09-26","cited_by_count":229},{"id":"2307.15266","title":"RSGPT: A Remote Sensing Vision Language Model and Benchmark","created":"2023-07-28","cited_by_count":207},{"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":"1802.08714","title":"Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction","created":"2018-02-23","cited_by_count":162},{"id":"2104.14917","title":"Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution","created":"2021-04-30","cited_by_count":157},{"id":"2310.09751","title":"UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting","created":"2023-10-15","cited_by_count":144},{"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":"1906.11172","title":"Learning Data Augmentation Strategies for Object Detection","created":"2019-06-26","cited_by_count":139},{"id":"2312.03606","title":"DiffusionSat: A Generative Foundation Model for Satellite Imagery","created":"2023-12-06","cited_by_count":131},{"id":"2306.08259","title":"LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting","created":"2023-06-14","cited_by_count":118},{"id":"2205.14204","title":"Multimodal Masked Autoencoders Learn Transferable Representations","created":"2022-05-27","cited_by_count":109},{"id":"2002.12204","title":"Visual Commonsense R-CNN","created":"2020-02-27","cited_by_count":106},{"id":"2306.11222","title":"LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation","created":"2023-06-20","cited_by_count":104},{"id":"2305.13711","title":"LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models","created":"2023-05-23","cited_by_count":101},{"id":"2205.01491","title":"A Comprehensive Survey of Image Augmentation Techniques for Deep Learning","created":"2022-05-03","cited_by_count":97},{"id":"2308.15197","title":"Where Would I Go Next? Large Language Models as Human Mobility Predictors","created":"2023-08-29","cited_by_count":93},{"id":"2002.05786","title":"Deep Learning for Financial Applications : A Survey","created":"2020-02-09","cited_by_count":91},{"id":"2303.07226","title":"Scaling Vision-Language Models with Sparse Mixture of Experts","created":"2023-03-13","cited_by_count":88},{"id":"2301.13629","title":"DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Models","created":"2023-01-31","cited_by_count":81},{"id":"2112.03806","title":"OOD-GNN: Out-of-Distribution Generalized Graph Neural Network","created":"2021-12-07","cited_by_count":78},{"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":"2002.08596","title":"Interpretability of machine learning based prediction models in healthcare","created":"2020-02-20","cited_by_count":75},{"id":"2211.15979","title":"AirFormer: Predicting Nationwide Air Quality in China with Transformers","created":"2022-11-29","cited_by_count":73},{"id":"2010.06988","title":"Using satellite imagery to understand and promote sustainable development","created":"2020-09-23","cited_by_count":71},{"id":"2101.06462","title":"Dual-Level Collaborative Transformer for Image Captioning","created":"2021-01-16","cited_by_count":71},{"id":"2306.00020","title":"GPT4GEO: How a Language Model Sees the World's Geography","created":"2023-05-30","cited_by_count":68},{"id":"2208.02131","title":"Masked Vision and Language Modeling for Multi-modal Representation Learning","created":"2022-08-03","cited_by_count":67},{"id":"2310.06213","title":"GeoLLM: Extracting Geospatial Knowledge from Large Language Models","created":"2023-10-10","cited_by_count":64},{"id":"1905.10069","title":"STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting","created":"2019-05-24","cited_by_count":60},{"id":"2002.12898","title":"PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecasting","created":"2020-02-10","cited_by_count":55},{"id":"2110.04038","title":"Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network","created":"2021-10-08","cited_by_count":52},{"id":"2209.05479","title":"Leveraging Language Foundation Models for Human Mobility Forecasting","created":"2022-09-11","cited_by_count":50},{"id":"2309.13378","title":"Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment","created":"2023-09-23","cited_by_count":47},{"id":"2208.12397","title":"Causal Inference in Recommender Systems: A Survey and Future Directions","created":"2022-08-26","cited_by_count":44},{"id":"2302.06232","title":"Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data","created":"2023-02-13","cited_by_count":43},{"id":"2008.03686","title":"Local Differential Privacy and Its Applications: A Comprehensive Survey","created":"2020-08-09","cited_by_count":41},{"id":"1903.07789","title":"Predicting Citywide Crowd Flows in Irregular Regions Using Multi-View Graph Convolutional Networks","created":"2019-03-19","cited_by_count":40},{"id":"2402.17161","title":"Large Language Model for Participatory Urban Planning","created":"2024-02-27","cited_by_count":40},{"id":"2312.11813","title":"Urban Generative Intelligence (UGI): A Foundational Platform for Agents in Embodied City Environment","created":"2023-12-19","cited_by_count":37},{"id":"2008.08903","title":"Generative Adversarial Networks for Spatio-temporal Data: A Survey","created":"2020-08-18","cited_by_count":35},{"id":"1701.02543","title":"Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks","created":"2017-01-10","cited_by_count":34},{"id":"2209.06389","title":"Jointly Contrastive Representation Learning on Road Network and Trajectory","created":"2022-09-14","cited_by_count":34},{"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":"2306.09821","title":"Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System","created":"2023-06-16","cited_by_count":32},{"id":"1902.05377","title":"UrbanFM: Inferring Fine-Grained Urban Flows","created":"2019-02-06","cited_by_count":31},{"id":"2206.02353","title":"Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data","created":"2022-06-06","cited_by_count":27},{"id":"2203.09127","title":"ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps","created":"2022-03-17","cited_by_count":25},{"id":"2111.03465","title":"Spatio-Temporal Urban Knowledge Graph Enabled Mobility Prediction","created":"2021-11-01","cited_by_count":24},{"id":"2211.08975","title":"Region Embedding with Intra and Inter-View Contrastive Learning","created":"2022-11-15","cited_by_count":24},{"id":"2302.13094","title":"Knowledge-infused Contrastive Learning for Urban Imagery-based Socioeconomic Prediction","created":"2023-02-25","cited_by_count":23},{"id":"2302.10897","title":"Learning to Simulate Daily Activities via Modeling Dynamic Human Needs","created":"2023-02-09","cited_by_count":20},{"id":"2308.03333","title":"Heterogeneous Knowledge Fusion: A Novel Approach for Personalized Recommendation via LLM","created":"2023-08-07","cited_by_count":18},{"id":"2310.08096","title":"ClimateBERT-NetZero: Detecting and Assessing Net Zero and Reduction Targets","created":"2023-10-12","cited_by_count":17},{"id":"2011.05602","title":"Joint predictions of multi-modal ride-hailing demands: a deep multi-task multigraph learning-based approach","created":"2020-11-11","cited_by_count":16},{"id":"2212.00904","title":"Human-instructed Deep Hierarchical Generative Learning for Automated Urban Planning","created":"2022-12-01","cited_by_count":15},{"id":"2110.07717","title":"Deep Human-guided Conditional Variational Generative Modeling for Automated Urban Planning","created":"2021-10-12","cited_by_count":13}],"next_cursor":"100"}