{"total":12,"rows":[{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208,"area":null},{"id":"2407.15762","title":"Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning","created":"2024-07-22","cited_by_count":43,"area":null},{"id":"2410.15557","title":"How to Find the Exact Pareto Front for Multi-Objective MDPs?","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2409.10683","title":"MotIF: Motion Instruction Fine-tuning","created":"2024-09-16","cited_by_count":4,"area":null},{"id":"2509.19843","title":"PersONAL: Towards a Comprehensive Benchmark for Personalized Embodied Agents","created":"2025-09-24","cited_by_count":4,"area":null},{"id":"2411.00524","title":"Comparison-based Active Preference Learning for Multi-dimensional Personalization","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2503.05035","title":"QuietPaw: Learning Quadrupedal Locomotion with Versatile Noise Preference Alignment","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2505.00490","title":"Optimal Interactive Learning on the Job via Facility Location Planning","created":"2025-05-01","cited_by_count":2,"area":null},{"id":"2606.01313","title":"PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2606.32027","title":"Freeform Preference Learning for Robotic Manipulation","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2605.27013","title":"Generating Robust Portfolios of Optimization Models using Large Language Models","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2609.39055","title":"The Missing Coefficients: Bayesian Pairwise Merging for Model Personalization","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}