{"total":16,"rows":[{"id":"2412.03578","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","created":"2024-11-18","cited_by_count":24,"area":null},{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2402.05367","title":"Principled Preferential Bayesian Optimization","created":"2024-02-08","cited_by_count":16,"area":null},{"id":"2404.03745","title":"Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinations","created":"2024-04-04","cited_by_count":12,"area":null},{"id":"2510.08539","title":"On the optimization dynamics of RLVR: Gradient gap and step size thresholds","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2602.09456","title":"Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2505.11983","title":"Online Iterative Self-Alignment for Radiology Report Generation","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2403.08199","title":"Deep Submodular Peripteral Networks","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2410.11444","title":"A Theoretical Survey on Foundation Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2410.14715","title":"Animating the Past: Reconstruct Trilobite via Video Generation","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2504.15812","title":"Fusing Reward and Dueling Feedback in Stochastic Bandits","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2511.00220","title":"Iterative Foundation Model Fine-Tuning on Multiple Rewards","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2606.27082","title":"Finding Stationary Points by Comparisons","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2601.19055","title":"Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2604.02349","title":"OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2606.08410","title":"Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries","created":"2026-06-07","cited_by_count":0,"area":null}],"next_cursor":null}