{"total":74,"rows":[{"id":"2005.02575","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","created":"2020-05-06","cited_by_count":71,"area":"alignment"},{"id":"2111.12306","title":"Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability","created":"2021-11-24","cited_by_count":44,"area":null},{"id":"2203.11382","title":"Preference Exploration for Efficient Bayesian Optimization with Multiple Outcomes","created":"2022-03-21","cited_by_count":42,"area":null},{"id":"2212.04450","title":"GAUCHE: A Library for Gaussian Processes in Chemistry","created":"2022-12-06","cited_by_count":41,"area":null},{"id":"2202.04593","title":"Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models","created":"2022-02-09","cited_by_count":37,"area":null},{"id":"2206.07438","title":"Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overview","created":"2022-06-15","cited_by_count":37,"area":null},{"id":"2310.17273","title":"Looping in the Human Collaborative and Explainable Bayesian Optimization","created":"2023-10-26","cited_by_count":27,"area":null},{"id":"2303.15746","title":"qEUBO: A Decision-Theoretic Acquisition Function for Preferential Bayesian Optimization","created":"2023-03-28","cited_by_count":23,"area":null},{"id":"2302.01513","title":"Towards Practical Preferential Bayesian Optimization with Skew Gaussian Processes","created":"2023-02-03","cited_by_count":19,"area":null},{"id":"2405.00981","title":"Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitation","created":"2024-05-02","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":"2411.01493","title":"Sample-Efficient Alignment for LLMs","created":"2024-11-03","cited_by_count":16,"area":"alignment"},{"id":"2311.13460","title":"Multi-Objective Bayesian Optimization with Active Preference Learning","created":"2023-11-22","cited_by_count":13,"area":null},{"id":"2202.11795","title":"Exploiting Correlation to Achieve Faster Learning Rates in Low-Rank Preference Bandits","created":"2022-02-23","cited_by_count":11,"area":null},{"id":"2306.13104","title":"Human-in-the-Loop Optimization for Deep Stimulus Encoding in Visual Prostheses","created":"2023-06-16","cited_by_count":8,"area":null},{"id":"2503.00924","title":"PABBO: Preferential Amortized Black-Box Optimization","created":"2025-03-02","cited_by_count":8,"area":null},{"id":"2406.16745","title":"Bandits with Preference Feedback: A Stackelberg Game Perspective","created":"2024-06-24","cited_by_count":7,"area":"alignment"},{"id":"2605.17976","title":"Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery","created":"2026-05-18","cited_by_count":7,"area":null},{"id":"2107.13074","title":"Toward AI Assistants That Let Designers Design","created":"2021-07-22","cited_by_count":6,"area":null},{"id":"2205.13662","title":"Explaining Preferences with Shapley Values","created":"2022-05-26","cited_by_count":6,"area":null},{"id":"2208.08742","title":"Bayesian Optimization Augmented with Actively Elicited Expert Knowledge","created":"2022-08-18","cited_by_count":6,"area":null},{"id":"2210.02562","title":"Dueling Convex Optimization with General Preferences","created":"2022-09-27","cited_by_count":6,"area":null},{"id":"2511.02966","title":"Inference-Time Personalized Alignment with a Few User Preference Queries","created":"2025-11-04","cited_by_count":6,"area":null},{"id":"2110.09361","title":"Efficient Exploration in Binary and Preferential Bayesian Optimization","created":"2021-10-18","cited_by_count":5,"area":null},{"id":"2410.10452","title":"Principled Bayesian Optimisation in Collaboration with Human Experts","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2501.18873","title":"Best Policy Learning from Trajectory Preference Feedback","created":"2025-01-31","cited_by_count":5,"area":"alignment"},{"id":"2111.00639","title":"End-to-End Learning of Deep Kernel Acquisition Functions for Bayesian Optimization","created":"2021-11-01","cited_by_count":4,"area":null},{"id":"2308.04571","title":"Optimizing Algorithms From Pairwise User Preferences","created":"2023-08-08","cited_by_count":4,"area":null},{"id":"2410.09290","title":"Ranking over Regression for Bayesian Optimization and Molecule Selection","created":"2024-10-11","cited_by_count":4,"area":null},{"id":"2411.05899","title":"Streaming Bayes GFlowNets","created":"2024-11-08","cited_by_count":4,"area":null},{"id":"2103.13192","title":"On Preference Learning Based on Sequential Bayesian Optimization with Pairwise Comparison","created":"2021-03-24","cited_by_count":3,"area":null},{"id":"2107.12809","title":"Bayesian Optimisation for Sequential Experimental Design with Applications in Additive Manufacturing","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2202.01125","title":"GLISp-r: A preference-based optimization algorithm with convergence guarantees","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2402.17343","title":"Enhanced Bayesian Optimization via Preferential Modeling of Abstract Properties","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2406.06459","title":"How Useful is Intermittent, Asynchronous Expert Feedback for Bayesian Optimization?","created":"2024-06-10","cited_by_count":3,"area":"alignment"},{"id":"2406.14699","title":"Preferential Multi-Objective Bayesian Optimization","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2505.23673","title":"Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds","created":"2025-05-29","cited_by_count":3,"area":"alignment"},{"id":"2110.08217","title":"Choice functions based multi-objective Bayesian optimisation","created":"2021-10-15","cited_by_count":2,"area":null},{"id":"2409.11535","title":"Balancing Optimality and Diversity: Human-Centered Decision Making through Generative Curation","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2504.03744","title":"Comparative Explanations: Explanation Guided Decision Making for Human-in-the-Loop Preference Selection","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2507.15355","title":"Efficient Visual Appearance Optimization by Learning from Prior Preferences","created":"2025-07-21","cited_by_count":2,"area":null},{"id":"2507.16999","title":"Bayesian preference elicitation for decision support in multiobjective optimization","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2509.16176","title":"Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories","created":"2025-09-19","cited_by_count":2,"area":"agents"},{"id":"2511.04286","title":"Efficient Reinforcement Learning from Human Feedback via Bayesian Preference Inference","created":"2025-11-06","cited_by_count":2,"area":"alignment"},{"id":"2111.03447","title":"Contextual Bayesian optimization with binary outputs","created":"2021-11-05","cited_by_count":1,"area":null},{"id":"2302.05665","title":"The Impact of Expertise in the Loop for Exploring Machine Rationality","created":"2023-02-11","cited_by_count":1,"area":null},{"id":"2405.14657","title":"Anchor-Based Heteroscedastic Noise for Preferential Bayesian Optimization","created":"2024-05-23","cited_by_count":1,"area":null},{"id":"2501.18792","title":"Bayesian Optimization with Preference Exploration using a Monotonic Neural Network Ensemble","created":"2025-01-30","cited_by_count":1,"area":null},{"id":"2508.10642","title":"A Guide to Bayesian Optimization in Bioprocess Engineering","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2509.04290","title":"An Interactive Framework for Finding the Optimal Trade-off in Differential Privacy","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2511.23141","title":"Automated Discovery of Laser Dicing Processes with Bayesian Optimization for Semiconductor Manufacturing","created":"2025-11-28","cited_by_count":1,"area":null},{"id":"2601.22335","title":"Knowledge Gradient for Preference Learning","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2603.24138","title":"Efficient Controller Learning from Human Preferences and Numerical Data Via Multi-Modal Surrogate Models","created":"2026-03-25","cited_by_count":1,"area":"alignment"},{"id":"2608.28620","title":"Preference Elicitation for Policy Optimization and Application to Aligning Heart Transplantation with Human Values","created":"2026-07-29","cited_by_count":1,"area":"alignment"},{"id":"2202.01468","title":"A unified surrogate-based scheme for black-box and preference-based optimization","created":"2022-02-03","cited_by_count":0,"area":null},{"id":"2302.14630","title":"Experience in Engineering Complex Systems: Active Preference Learning with Multiple Outcomes and Certainty Levels","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2310.00750","title":"Identifying Copeland Winners in Dueling Bandits with Indifferences","created":"2023-10-01","cited_by_count":0,"area":null},{"id":"2402.02687","title":"Poisson Process for Bayesian Optimization","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2404.19693","title":"SwipeGANSpace: Swipe-to-Compare Image Generation via Efficient Latent Space Exploration","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2507.13491","title":"Model-free Reinforcement Learning for Model-based Control: Towards Safe, Interpretable and Sample-efficient Agents","created":"2025-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2511.04751","title":"Regularized GLISp for sensor-guided human-in-the-loop optimization","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2511.05163","title":"Consecutive Preferential Bayesian Optimization","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2512.14263","title":"DT-PBO: an Interpretable Tree-based Surrogate Model for Preferential Bayesian Optimization","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.04713","title":"Adaptive Prompt Elicitation for Text-to-Image Generation","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2604.25025","title":"A Finite Time Analysis of Thompson Sampling for Bayesian Optimization with Preferential Feedback","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.12079","title":"Elicitation-Augmented Bayesian Optimization","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.19151","title":"Progressive Autonomy as Preference Learning: A Formalization of Trust Calibration for Agentic Tool Use","created":"2026-05-18","cited_by_count":0,"area":"agents"},{"id":"2605.26072","title":"Active Query Synthesis for Preference Learning","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.02351","title":"Local Preferential Bayesian Optimization","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2608.07859","title":"Adaptive KappaSharp: Condition-Number Shaping for Preferential Bayesian Optimization","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2609.28427","title":"Context-Continuous Preference Learning for Exoskeleton Personalization","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.01827","title":"Scientific Discovery under Validation Congestion via Multi-Fidelity Pairwise Rankings","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.03824","title":"Targeted Active Learning for Preference-Based Treatment Effects on Multivariate Outcomes","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.14757","title":"Rethinking Opinion Measurement Interfaces for Human-in-the-Loop Optimization","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}