{"total":15,"rows":[{"id":"2312.14037","title":"Neural Contextual Bandits for Personalized Recommendation","created":"2023-12-21","cited_by_count":10,"area":null},{"id":"2404.15691","title":"Long-term Off-Policy Evaluation and Learning","created":"2024-04-24","cited_by_count":9,"area":null},{"id":"2408.05586","title":"Meta Clustering of Neural Bandits","created":"2024-08-10","cited_by_count":7,"area":null},{"id":"2506.11898","title":"Martingale Posterior Neural Networks for Fast Sequential Decision Making","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2511.10492","title":"Don't Waste It: Guiding Generative Recommenders with Structured Human Priors via Multi-Head Decoding","created":"2025-11-13","cited_by_count":3,"area":null},{"id":"2406.01611","title":"System-2 Recommenders: Disentangling Utility and Engagement in Recommendation Systems via Temporal Point-Processes","created":"2024-05-29","cited_by_count":2,"area":null},{"id":"2408.14432","title":"Contextual Bandit with Herding Effects: Algorithms and Recommendation Applications","created":"2024-08-26","cited_by_count":1,"area":null},{"id":"2510.00309","title":"Lipschitz Bandits with Stochastic Delayed Feedback","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2308.01028","title":"Maximizing Success Rate of Payment Routing using Non-stationary Bandits","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2407.03674","title":"Short-Long Policy Evaluation with Novel Actions","created":"2024-07-04","cited_by_count":0,"area":null},{"id":"2412.20638","title":"Predicting Long Term Sequential Policy Value Using Softer Surrogates","created":"2024-12-30","cited_by_count":0,"area":null},{"id":"2503.17674","title":"MultiScale Contextual Bandits for Long Term Objectives","created":"2025-03-22","cited_by_count":0,"area":null},{"id":"2602.15752","title":"Beyond Match Maximization and Fairness: Retention-Optimized Two-Sided Matching","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2602.22913","title":"SIGMA: A Semantic-Grounded Instruction-Driven Generative Multi-Task Recommender at AliExpress","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2604.00915","title":"Orthogonal Learner for Estimating Heterogeneous Long-Term Treatment Effects","created":"2026-04-01","cited_by_count":0,"area":null}],"next_cursor":null}