{"total":17,"rows":[{"id":"2501.10945","title":"Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond","created":"2025-01-19","cited_by_count":18,"area":null},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2402.16565","title":"Partial Rankings of Optimizers","created":"2024-02-26","cited_by_count":8,"area":null},{"id":"2406.18924","title":"Learning Pareto Set for Multi-Objective Continuous Robot Control","created":"2024-06-27","cited_by_count":8,"area":null},{"id":"2305.14782","title":"IBCL: Zero-shot Model Generation under Stability-Plasticity Trade-offs","created":"2023-05-24","cited_by_count":5,"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":"2410.16398","title":"Federated Communication-Efficient Multi-Objective Optimization","created":"2024-10-21","cited_by_count":3,"area":null},{"id":"2603.06748","title":"Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2408.09976","title":"Preference-Optimized Pareto Set Learning for Blackbox Optimization","created":"2024-08-19","cited_by_count":2,"area":null},{"id":"2506.08062","title":"FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2303.08909","title":"Latent-Conditioned Policy Gradient for Multi-Objective Deep Reinforcement Learning","created":"2023-03-15","cited_by_count":1,"area":null},{"id":"2601.22350","title":"Learning Policy Representations for Steerable Behavior Synthesis","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2603.22813","title":"Learning What Matters Now: Dynamic Preference Inference under Contextual Shifts","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2608.04999","title":"ORACLE: A Multi-Objective Reinforcement Learning-Based Analog Circuit Design Optimizer with Large Language Models-Guided Exploration","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2603.02628","title":"Post Hoc Extraction of Pareto Fronts for Continuous Control","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2606.14693","title":"Learning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2609.17992","title":"The Operable Pareto Front: Distilling Offline Search into Run-Time Control for Multi-Objective UAV Edge-Computing Scheduling","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}