{"total":30,"rows":[{"id":"2302.08242","title":"Tuning computer vision models with task rewards","created":"2023-02-16","cited_by_count":37,"area":null},{"id":"2112.10948","title":"Task-Oriented Image Transmission for Scene Classification in Unmanned Aerial Systems","created":"2021-12-21","cited_by_count":30,"area":null},{"id":"2305.17473","title":"A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU","created":"2023-05-27","cited_by_count":25,"area":null},{"id":"2202.03609","title":"PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning","created":"2022-02-08","cited_by_count":19,"area":null},{"id":"2310.04716","title":"Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API","created":"2023-10-07","cited_by_count":18,"area":null},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2306.10225","title":"Genes in Intelligent Agents","created":"2023-06-17","cited_by_count":9,"area":null},{"id":"2207.05225","title":"Susceptibility of Continual Learning Against Adversarial Attacks","created":"2022-07-11","cited_by_count":8,"area":null},{"id":"2311.02719","title":"Uncertainty Estimation for Safety-critical Scene Segmentation via Fine-grained Reward Maximization","created":"2023-11-05","cited_by_count":7,"area":null},{"id":"2405.11467","title":"AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation","created":"2024-05-19","cited_by_count":7,"area":null},{"id":"2409.19221","title":"Cauchy activation function and XNet","created":"2024-09-28","cited_by_count":5,"area":null},{"id":"2308.13270","title":"A Game of Bundle Adjustment -- Learning Efficient Convergence","created":"2023-08-25","cited_by_count":4,"area":null},{"id":"2210.06297","title":"Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning","created":"2022-09-30","cited_by_count":3,"area":null},{"id":"2505.18514","title":"Test-Time Adaptation with Binary Feedback","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2204.07543","title":"CryoRL: Reinforcement Learning Enables Efficient Cryo-EM Data Collection","created":"2022-04-15","cited_by_count":1,"area":null},{"id":"2207.03091","title":"Online SuBmodular + SuPermodular (BP) Maximization with Bandit Feedback","created":"2022-07-07","cited_by_count":1,"area":null},{"id":"2210.00828","title":"Mastering Spatial Graph Prediction of Road Networks","created":"2022-10-03","cited_by_count":1,"area":null},{"id":"2305.14216","title":"Constrained Proximal Policy Optimization","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2310.20057","title":"SolarFormer: Multi-scale Transformer for Solar PV Profiling","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2311.13731","title":"A Survey of Blockchain, Artificial Intelligence, and Edge Computing for Web 3.0","created":"2023-11-22","cited_by_count":1,"area":null},{"id":"2404.11429","title":"CarcassFormer: An End-to-end Transformer-based Framework for Simultaneous Localization, Segmentation and Classification of Poultry Carcass Defect","created":"2024-04-17","cited_by_count":1,"area":null},{"id":"2407.01017","title":"Coding for Intelligence from the Perspective of Category","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2411.05780","title":"GazeSearch: Radiology Findings Search Benchmark","created":"2024-11-08","cited_by_count":1,"area":null},{"id":"2503.00191","title":"Learning Vision-Based Neural Network Controllers with Semi-Probabilistic Safety Guarantees","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2205.14042","title":"Reinforced Pedestrian Attribute Recognition with Group Optimization Reward","created":"2022-05-21","cited_by_count":0,"area":null},{"id":"2305.12088","title":"Game-Theoretical Analysis of Reviewer Rewards in Peer-Review Journal Systems: Analysis and Experimental Evaluation using Deep Reinforcement Learning","created":"2023-05-20","cited_by_count":0,"area":null},{"id":"2307.05232","title":"A Survey From Distributed Machine Learning to Distributed Deep Learning","created":"2023-07-11","cited_by_count":0,"area":null},{"id":"2307.10085","title":"A Decision Making Framework for Recommended Maintenance of Road Segments","created":"2023-07-19","cited_by_count":0,"area":null},{"id":"2309.02712","title":"Unveiling the frontiers of deep learning: innovations shaping diverse domains","created":"2023-09-06","cited_by_count":0,"area":null}],"next_cursor":null}