{"list":"other","total":105,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"2003.01332","title":"Heterogeneous Graph Transformer","created":"2020-03-03","cited_by_count":582},{"id":"1911.06455","title":"Graph Transformer Networks","created":"2019-11-06","cited_by_count":523},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"2103.14023","title":"AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting","created":"2021-03-25","cited_by_count":331},{"id":"1908.08593","title":"Revealing the Dark Secrets of BERT","created":"2019-08-21","cited_by_count":301},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"2006.15595","title":"Rethinking Positional Encoding in Language Pre-training","created":"2020-06-28","cited_by_count":197},{"id":"2101.06286","title":"Reinforcement learning based recommender systems: A survey","created":"2021-01-15","cited_by_count":188},{"id":"1810.07862","title":"Applications of Deep Reinforcement Learning in Communications and Networking: A Survey","created":"2018-10-18","cited_by_count":167},{"id":"1905.07799","title":"Adaptive Attention Span in Transformers","created":"2019-05-19","cited_by_count":149},{"id":"2202.09481","title":"TransDreamer: Reinforcement Learning with Transformer World Models","created":"2022-02-19","cited_by_count":143},{"id":"2007.04825","title":"Fast Transformers with Clustered Attention","created":"2020-07-09","cited_by_count":123},{"id":"2209.03993","title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","created":"2022-09-08","cited_by_count":103},{"id":"1911.05321","title":"IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data","created":"2019-11-13","cited_by_count":86},{"id":"2405.10825","title":"Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities","created":"2024-05-17","cited_by_count":83},{"id":"2205.15967","title":"You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments","created":"2022-05-31","cited_by_count":63},{"id":"2105.04371","title":"Poolingformer: Long Document Modeling with Pooling Attention","created":"2021-05-10","cited_by_count":60},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50},{"id":"2006.03555","title":"Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers","created":"2020-06-05","cited_by_count":49},{"id":"1803.08375","title":"Deep Learning using Rectified Linear Units (ReLU)","created":"2018-03-22","cited_by_count":48},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46},{"id":"1810.10182","title":"Modeling Localness for Self-Attention Networks","created":"2018-10-24","cited_by_count":43},{"id":"2206.01078","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","created":"2022-06-02","cited_by_count":36},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36},{"id":"1810.10183","title":"Multi-Head Attention with Disagreement Regularization","created":"2018-10-24","cited_by_count":35},{"id":"2202.13110","title":"Optimal-er Auctions through Attention","created":"2022-02-26","cited_by_count":27},{"id":"2307.07146","title":"Federated Learning-Empowered AI-Generated Content in Wireless Networks","created":"2023-07-14","cited_by_count":26},{"id":"2402.18587","title":"At the Dawn of Generative AI Era: A Tutorial-cum-Survey on New Frontiers in 6G Wireless Intelligence","created":"2024-02-02","cited_by_count":25},{"id":"2412.19823","title":"A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directions","created":"2024-12-16","cited_by_count":25},{"id":"2103.15332","title":"Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark","created":"2021-03-29","cited_by_count":23},{"id":"2207.10295","title":"Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning","created":"2022-07-21","cited_by_count":22},{"id":"2107.05431","title":"CoBERL: Contrastive BERT for Reinforcement Learning","created":"2021-07-12","cited_by_count":21},{"id":"2112.10433","title":"Diaformer: Automatic Diagnosis via Symptoms Sequence Generation","created":"2021-12-20","cited_by_count":19},{"id":"1912.00544","title":"Multi-Scale Self-Attention for Text Classification","created":"2019-12-02","cited_by_count":16},{"id":"2404.05199","title":"Decision Transformers for Wireless Communications: A New Paradigm of Resource Management","created":"2024-04-08","cited_by_count":15},{"id":"2405.17454","title":"Generative AI for the Optimization of Next-Generation Wireless Networks: Basics, State-of-the-Art, and Open Challenges","created":"2024-05-22","cited_by_count":14},{"id":"1904.03100","title":"Information Aggregation for Multi-Head Attention with Routing-by-Agreement","created":"2019-04-05","cited_by_count":13},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12},{"id":"2405.20568","title":"Generative AI for Deep Reinforcement Learning: Framework, Analysis, and Use Cases","created":"2024-05-31","cited_by_count":12},{"id":"2301.00362","title":"Goal-Guided Transformer-Enabled Reinforcement Learning for Efficient Autonomous Navigation","created":"2023-01-01","cited_by_count":10},{"id":"2305.00135","title":"Joint Sensing, Communication, and AI: A Trifecta for Resilient THz User Experiences","created":"2023-04-29","cited_by_count":10},{"id":"2301.05334","title":"TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems","created":"2023-01-13","cited_by_count":9},{"id":"2308.14020","title":"A Comparison of Neural Networks for Wireless Channel Prediction","created":"2023-08-27","cited_by_count":8},{"id":"1909.00188","title":"Improving Multi-Head Attention with Capsule Networks","created":"2019-08-31","cited_by_count":6},{"id":"2410.14348","title":"TF-DDRL: A Transformer-enhanced Distributed DRL Technique for Scheduling IoT Applications in Edge and Cloud Computing Environments","created":"2024-10-18","cited_by_count":6},{"id":"2406.05418","title":"Multi-attribute Auction-based Resource Allocation for Twins Migration in Vehicular Metaverses: A GPT-based DRL Approach","created":"2024-06-08","cited_by_count":5},{"id":"2401.01589","title":"The Security and Privacy of Mobile Edge Computing: An Artificial Intelligence Perspective","created":"2024-01-03","cited_by_count":4},{"id":"2407.13113","title":"Multiobjective Vehicle Routing Optimization with Time Windows: A Hybrid Approach Using Deep Reinforcement Learning and NSGA-II","created":"2024-07-18","cited_by_count":4},{"id":"2502.18196","title":"Machine Learning for Future Wireless Communications: Channel Prediction Perspectives","created":"2025-02-25","cited_by_count":4},{"id":"2404.09905","title":"Quality of Experience Oriented Cross-layer Optimization for Real-time XR Video Transmission","created":"2024-04-15","cited_by_count":3},{"id":"2405.07759","title":"MADRL-Based Rate Adaptation for 360{\\deg} Video Streaming with Multi-Viewpoint Prediction","created":"2024-05-13","cited_by_count":3},{"id":"2410.23031","title":"Offline Reinforcement Learning and Sequence Modeling for Downlink Link Adaptation","created":"2024-10-30","cited_by_count":3},{"id":"2503.08937","title":"Beam Selection in ISAC using Contextual Bandit with Multi-modal Transformer and Transfer Learning","created":"2025-03-11","cited_by_count":3},{"id":"2505.22170","title":"Attention-Enhanced Prompt Decision Transformers for UAV-Assisted Communications with AoI","created":"2025-05-28","cited_by_count":3},{"id":"2507.09094","title":"Transformer based Collaborative Reinforcement Learning for Fluid Antenna System (FAS)-enabled 3D UAV Positioning","created":"2025-07-12","cited_by_count":3},{"id":"2307.03028","title":"Performance Analysis and Approximate Message Passing Detection of Orthogonal Time Sequency Multiplexing Modulation","created":"2023-07-06","cited_by_count":2},{"id":"2309.03771","title":"Space-Time Shift Keying Aided OTFS Modulation for Orthogonal Multiple Access","created":"2023-09-07","cited_by_count":2},{"id":"2309.16935","title":"TranDRL: A Transformer-Driven Deep Reinforcement Learning Enabled Prescriptive Maintenance Framework","created":"2023-09-29","cited_by_count":2},{"id":"2312.11739","title":"TPTO: A Transformer-PPO based Task Offloading Solution for Edge Computing Environments","created":"2023-12-18","cited_by_count":2},{"id":"2404.04692","title":"Securing the Skies: An IRS-Assisted AoI-Aware Secure Multi-UAV System with Efficient Task Offloading","created":"2024-04-06","cited_by_count":2},{"id":"2501.15468","title":"Low-altitude UAV Friendly-Jamming for Satellite-Maritime Communications via Generative AI-enabled Deep Reinforcement Learning","created":"2025-01-26","cited_by_count":2},{"id":"2305.09953","title":"Low Complexity Detection of Spatial Modulation Aided OTFS in Doubly-Selective Channels","created":"2023-05-17","cited_by_count":1},{"id":"2306.17183","title":"Deep Reinforcement Learning for Privacy-Preserving Task Offloading in Integrated Satellite-Terrestrial Networks","created":"2023-06-20","cited_by_count":1},{"id":"2407.03729","title":"Charging Ahead: A Hierarchical Adversarial Framework for Counteracting Advanced Cyber Threats in EV Charging Stations","created":"2024-07-04","cited_by_count":1},{"id":"2408.05505","title":"RIS-Assisted Cell-Free Massive MIMO Relying on Reflection Pattern Modulation","created":"2024-08-10","cited_by_count":1},{"id":"2501.10865","title":"Generalized Spatial Modulation Aided Affine Frequency Division Multiplexing","created":"2025-01-18","cited_by_count":1},{"id":"2501.12829","title":"A transformer-based deep q learning approach for dynamic load balancing in software-defined networks","created":"2025-01-22","cited_by_count":1}],"next_cursor":"100"}