{"total":2146,"rows":[{"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,"area":null},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210,"area":null},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827,"area":null},{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632,"area":null},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608,"area":null},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406,"area":null},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380,"area":null},{"id":"2103.14023","title":"AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting","created":"2021-03-25","cited_by_count":331,"area":null},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321,"area":null},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261,"area":null},{"id":"2103.04922","title":"Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models","created":"2021-03-08","cited_by_count":252,"area":null},{"id":"2103.00550","title":"A Survey on Deep Semi-supervised Learning","created":"2021-02-28","cited_by_count":251,"area":null},{"id":"2402.19427","title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","created":"2024-02-29","cited_by_count":242,"area":null},{"id":"2104.00681","title":"NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video","created":"2021-04-01","cited_by_count":241,"area":null},{"id":"2101.10318","title":"Multi-Time Attention Networks for Irregularly Sampled Time Series","created":"2021-01-25","cited_by_count":238,"area":null},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197,"area":null},{"id":"2112.00778","title":"Quantum advantage in learning from experiments","created":"2021-12-01","cited_by_count":188,"area":null},{"id":"2406.16964","title":"Are Language Models Actually Useful for Time Series Forecasting?","created":"2024-06-22","cited_by_count":168,"area":null},{"id":"2110.00987","title":"Motif-based Graph Self-Supervised Learning for Molecular Property Prediction","created":"2021-10-03","cited_by_count":159,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149,"area":null},{"id":"2205.08897","title":"FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting","created":"2022-05-18","cited_by_count":147,"area":null},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146,"area":null},{"id":"2307.03759","title":"A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection","created":"2023-07-07","cited_by_count":145,"area":null},{"id":"2308.12570","title":"StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Construction","created":"2023-08-24","cited_by_count":145,"area":null},{"id":"2103.01128","title":"InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring","created":"2021-03-01","cited_by_count":141,"area":null},{"id":"2204.02174","title":"Multi-View Transformer for 3D Visual Grounding","created":"2022-04-05","cited_by_count":140,"area":null},{"id":"2203.16265","title":"SeqTR: A Simple yet Universal Network for Visual Grounding","created":"2022-03-30","cited_by_count":139,"area":null},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136,"area":null},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136,"area":null},{"id":"2107.10043","title":"KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics","created":"2021-07-21","cited_by_count":132,"area":null},{"id":"2208.07239","title":"ROLAND: Graph Learning Framework for Dynamic Graphs","created":"2022-08-15","cited_by_count":132,"area":null},{"id":"2211.05244","title":"Deep Learning for Time Series Anomaly Detection: A Survey","created":"2022-11-09","cited_by_count":131,"area":null},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"area":null},{"id":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127,"area":null},{"id":"2103.16746","title":"Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark","created":"2021-03-31","cited_by_count":126,"area":null},{"id":"2104.15060","title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","created":"2021-04-30","cited_by_count":125,"area":null},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2106.06847","title":"Video Super-Resolution Transformer","created":"2021-06-12","cited_by_count":121,"area":null},{"id":"2108.04443","title":"AdaRNN: Adaptive Learning and Forecasting of Time Series","created":"2021-08-10","cited_by_count":121,"area":null},{"id":"2102.02611","title":"CKConv: Continuous Kernel Convolution For Sequential Data","created":"2021-02-04","cited_by_count":120,"area":null},{"id":"2107.12375","title":"Geometric Deep Learning on Molecular Representations","created":"2021-07-26","cited_by_count":113,"area":null},{"id":"2106.11342","title":"Dive into Deep Learning","created":"2021-06-21","cited_by_count":111,"area":null},{"id":"2210.15871","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2022-10-28","cited_by_count":111,"area":null},{"id":"2103.11555","title":"Context-aware Biaffine Localizing Network for Temporal Sentence Grounding","created":"2021-03-22","cited_by_count":107,"area":null},{"id":"2212.00922","title":"Navigating to Objects in the Real World","created":"2022-12-02","cited_by_count":106,"area":null},{"id":"2311.01933","title":"ForecastPFN: Synthetically-Trained Zero-Shot Forecasting","created":"2023-11-03","cited_by_count":104,"area":null},{"id":"2402.05956","title":"Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting","created":"2024-02-04","cited_by_count":104,"area":null},{"id":"2104.10054","title":"T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval","created":"2021-04-20","cited_by_count":103,"area":null},{"id":"2111.11344","title":"Modeling Irregular Time Series with Continuous Recurrent Units","created":"2021-11-22","cited_by_count":103,"area":null},{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102,"area":null},{"id":"2403.02901","title":"A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods","created":"2024-03-05","cited_by_count":102,"area":null},{"id":"2208.07998","title":"What Artificial Neural Networks Can Tell Us About Human Language Acquisition","created":"2022-08-17","cited_by_count":99,"area":null},{"id":"2209.14941","title":"EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding","created":"2022-09-29","cited_by_count":99,"area":null},{"id":"2103.16284","title":"Locate then Segment: A Strong Pipeline for Referring Image Segmentation","created":"2021-03-30","cited_by_count":98,"area":null},{"id":"2109.05257","title":"Towards a Rigorous Evaluation of Time-series Anomaly Detection","created":"2021-09-11","cited_by_count":97,"area":null},{"id":"2107.14293","title":"Self-Supervised Transformer for Sparse and Irregularly Sampled Multivariate Clinical Time-Series","created":"2021-07-29","cited_by_count":96,"area":null},{"id":"2202.14037","title":"Understanding Contrastive Learning Requires Incorporating Inductive Biases","created":"2022-02-28","cited_by_count":96,"area":null},{"id":"2107.13731","title":"UIBert: Learning Generic Multimodal Representations for UI Understanding","created":"2021-07-29","cited_by_count":95,"area":null},{"id":"2108.00298","title":"Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks","created":"2021-07-31","cited_by_count":95,"area":null},{"id":"2211.08064","title":"Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications","created":"2022-11-15","cited_by_count":92,"area":null},{"id":"2107.03377","title":"Long Short-Term Transformer for Online Action Detection","created":"2021-07-07","cited_by_count":88,"area":null},{"id":"2211.14701","title":"Spatio-Temporal Meta-Graph Learning for Traffic Forecasting","created":"2022-11-27","cited_by_count":88,"area":null},{"id":"2105.13495","title":"Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention","created":"2021-05-27","cited_by_count":87,"area":null},{"id":"2111.05803","title":"Gradients are Not All You Need","created":"2021-11-10","cited_by_count":86,"area":null},{"id":"2302.08888","title":"Multimodal Federated Learning via Contrastive Representation Ensemble","created":"2023-02-17","cited_by_count":86,"area":null},{"id":"2411.16575","title":"Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression","created":"2024-11-25","cited_by_count":85,"area":null},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2406.01967","title":"DrEureka: Language Model Guided Sim-To-Real Transfer","created":"2024-06-04","cited_by_count":83,"area":null},{"id":"2103.16381","title":"Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud","created":"2021-03-30","cited_by_count":81,"area":null},{"id":"2305.03010","title":"Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence","created":"2023-05-04","cited_by_count":81,"area":null},{"id":"2102.13303","title":"Graph-based Semi-supervised Learning: A Comprehensive Review","created":"2021-02-26","cited_by_count":79,"area":null},{"id":"2303.12799","title":"Time Series as Images: Vision Transformer for Irregularly Sampled Time Series","created":"2023-03-01","cited_by_count":79,"area":null},{"id":"2309.06440","title":"LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning","created":"2023-09-12","cited_by_count":79,"area":null},{"id":"2402.09268","title":"Transformers, parallel computation, and logarithmic depth","created":"2024-02-14","cited_by_count":79,"area":null},{"id":"2211.10181","title":"LVOS: A Benchmark for Long-term Video Object Segmentation","created":"2022-11-18","cited_by_count":77,"area":null},{"id":"2308.11131","title":"ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation","created":"2023-08-22","cited_by_count":77,"area":null},{"id":"2112.02753","title":"MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image","created":"2021-12-06","cited_by_count":74,"area":null},{"id":"2309.12659","title":"OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling","created":"2023-09-22","cited_by_count":74,"area":null},{"id":"2106.04051","title":"Graph-MLP: Node Classification without Message Passing in Graph","created":"2021-06-08","cited_by_count":73,"area":null},{"id":"2108.09091","title":"DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction","created":"2021-08-20","cited_by_count":73,"area":null},{"id":"2206.08332","title":"BYOL-Explore: Exploration by Bootstrapped Prediction","created":"2022-06-16","cited_by_count":73,"area":null},{"id":"2202.08408","title":"Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs","created":"2022-02-17","cited_by_count":72,"area":null},{"id":"2405.07344","title":"TKAN: Temporal Kolmogorov-Arnold Networks","created":"2024-05-12","cited_by_count":71,"area":null},{"id":"2101.11796","title":"DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents","created":"2021-01-28","cited_by_count":70,"area":null},{"id":"2203.01601","title":"Syntax-Aware Network for Handwritten Mathematical Expression Recognition","created":"2022-03-03","cited_by_count":68,"area":null},{"id":"2302.02515","title":"Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey","created":"2023-02-06","cited_by_count":68,"area":null},{"id":"2304.08481","title":"Neural Map Prior for Autonomous Driving","created":"2023-04-17","cited_by_count":68,"area":null},{"id":"2112.13548","title":"Responsive Listening Head Generation: A Benchmark Dataset and Baseline","created":"2021-12-27","cited_by_count":67,"area":null},{"id":"2205.12465","title":"FBNETGEN: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generation","created":"2022-05-25","cited_by_count":67,"area":null},{"id":"2106.13898","title":"Closed-form Continuous-time Neural Models","created":"2021-06-25","cited_by_count":65,"area":null},{"id":"2202.12938","title":"Assessing the State of Self-Supervised Human Activity Recognition using Wearables","created":"2022-02-22","cited_by_count":65,"area":null},{"id":"2303.05970","title":"Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception","created":"2023-03-10","cited_by_count":65,"area":null},{"id":"2104.05522","title":"Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx","created":"2021-04-12","cited_by_count":64,"area":null},{"id":"2111.12073","title":"Multi-Person 3D Motion Prediction with Multi-Range Transformers","created":"2021-11-23","cited_by_count":63,"area":null},{"id":"2305.14938","title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","created":"2023-05-24","cited_by_count":63,"area":null},{"id":"2402.10635","title":"ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling","created":"2024-02-16","cited_by_count":63,"area":null},{"id":"2108.12944","title":"Selective Differential Privacy for Language Modeling","created":"2021-08-30","cited_by_count":62,"area":null},{"id":"2109.06275","title":"MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks","created":"2021-09-13","cited_by_count":62,"area":null},{"id":"2303.01859","title":"POPGym: Benchmarking Partially Observable Reinforcement Learning","created":"2023-03-03","cited_by_count":62,"area":null}],"next_cursor":"100"}