{"total":20,"rows":[{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112,"area":null},{"id":"2205.11140","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","created":"2022-05-23","cited_by_count":81,"area":null},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2410.01112","title":"Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits","created":"2024-10-01","cited_by_count":8,"area":null},{"id":"2302.03805","title":"Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback","created":"2023-02-07","cited_by_count":7,"area":null},{"id":"2407.18488","title":"Conversational Dueling Bandits in Generalized Linear Models","created":"2024-07-26","cited_by_count":5,"area":null},{"id":"2307.11897","title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","created":"2023-07-21","cited_by_count":4,"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":"2312.17229","title":"Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources","created":"2023-12-28","cited_by_count":3,"area":null},{"id":"2503.05306","title":"Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2603.19221","title":"Online Learning and Equilibrium Computation with Ranking Feedback","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2403.15045","title":"DP-Dueling: Learning from Preference Feedback without Compromising User Privacy","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2605.12545","title":"CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference","created":"2026-05-09","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":"2512.19057","title":"Efficient Personalization of Generative Models via Optimal Experimental Design","created":"2025-12-22","cited_by_count":0,"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":"2609.39351","title":"On the Complexity of Preference-Based Bandits","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}