{"total":54,"rows":[{"id":"2505.06274","title":"PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model","created":"2025-05-06","cited_by_count":28,"area":"alignment"},{"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":"2405.19650","title":"Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimization","created":"2024-05-30","cited_by_count":16,"area":null},{"id":"2407.17466","title":"Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning","created":"2024-07-24","cited_by_count":15,"area":"deeprl"},{"id":"2505.20925","title":"Multi-objective Large Language Model Alignment with Hierarchical Experts","created":"2025-05-27","cited_by_count":13,"area":"alignment"},{"id":"2406.09770","title":"Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion","created":"2024-06-14","cited_by_count":11,"area":"moe"},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11,"area":"alignment"},{"id":"2409.02969","title":"LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch","created":"2024-09-04","cited_by_count":10,"area":null},{"id":"2412.01773","title":"FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning","created":"2024-12-02","cited_by_count":9,"area":null},{"id":"2502.20161","title":"Balanced Rate-Distortion Optimization in Learned Image Compression","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2510.00352","title":"AReUReDi: Annealed Rectified Updates for Refining Discrete Flows with Multi-Objective Guidance","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2410.08656","title":"radarODE-MTL: A Multi-Task Learning Framework with Eccentric Gradient Alignment for Robust Radar-Based ECG Reconstruction","created":"2024-10-11","cited_by_count":4,"area":null},{"id":"2410.21764","title":"Adaptive Online Mirror Descent for Tchebycheff Scalarization in Multi-Objective Learning","created":"2024-10-29","cited_by_count":4,"area":null},{"id":"2409.19617","title":"LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real World","created":"2024-09-29","cited_by_count":3,"area":"deeprl"},{"id":"2509.07945","title":"One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning","created":"2025-09-09","cited_by_count":3,"area":"wm"},{"id":"2510.20872","title":"MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search Directions","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2602.09538","title":"UniARM: Towards a Unified Autoregressive Reward Model for Multi-Objective Test-Time Alignment","created":"2026-02-10","cited_by_count":3,"area":"alignment"},{"id":"2604.24357","title":"DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Discrete Diffusion Models","created":"2026-04-27","cited_by_count":3,"area":"diffusion"},{"id":"2507.21049","title":"Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning","created":"2025-07-28","cited_by_count":2,"area":null},{"id":"2509.03244","title":"FoMEMO: Towards Foundation Models for Expensive Multi-objective Optimization","created":"2025-09-03","cited_by_count":2,"area":null},{"id":"2509.21058","title":"SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion","created":"2025-09-25","cited_by_count":2,"area":"diffusion"},{"id":"2510.18258","title":"NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2601.20753","title":"GraphAllocBench: A Flexible Benchmark for Preference-Conditioned Multi-Objective Policy Learning","created":"2026-01-28","cited_by_count":2,"area":"deeprl"},{"id":"2602.06869","title":"Uncovering Cross-Objective Interference in Multi-Objective Alignment","created":"2026-02-06","cited_by_count":2,"area":"alignment"},{"id":"2603.10302","title":"How to make the most of your masked language model for protein engineering","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2604.24532","title":"A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning","created":"2026-04-27","cited_by_count":2,"area":"deeprl"},{"id":"2606.03962","title":"Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"id":"2501.07251","title":"MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework","created":"2025-01-13","cited_by_count":1,"area":null},{"id":"2503.08849","title":"Learning Pareto manifolds in high dimensions: How can regularization help?","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2505.21438","title":"Measuring Fine-Grained Relatedness in Multitask Learning via Data Attribution","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2506.06715","title":"A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworks","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2506.06830","title":"EndoARSS: Adapting Spatially-Aware Foundation Model for Efficient Activity Recognition and Semantic Segmentation in Endoscopic Surgery","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2604.07610","title":"Auto-Configured Networks for Multi-Scale Multi-Output Time-Series Forecasting","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.08946","title":"A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets","created":"2026-05-09","cited_by_count":1,"area":"deeprl"},{"id":"2605.09094","title":"A Tale of Two Problems: Multi-Task Bilevel Learning Meets Equality Constrained Multi-Objective Optimization","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.10585","title":"Controllability in preference-conditioned multi-objective reinforcement learning","created":"2026-05-11","cited_by_count":1,"area":"deeprl"},{"id":"2605.19330","title":"MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2608.18982","title":"Monroe: A Molecular Foundation Model for In-Context Probabilistic Inference","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2504.02833","title":"Scalable Min-Max Optimization via Primal-Dual Exact Pareto Optimization","created":"2025-03-16","cited_by_count":0,"area":null},{"id":"2504.12419","title":"Standardization of Multi-Objective QUBOs","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2511.06686","title":"Balancing Multi-modal Sensor Learning via Multi-objective Optimization","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2602.00478","title":"Quality-Diversity Optimization as Multi-Objective Optimization","created":"2026-01-31","cited_by_count":0,"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":"2604.13175","title":"Pareto-Optimal Offline Reinforcement Learning via Smooth Tchebycheff Scalarization","created":"2026-04-14","cited_by_count":0,"area":"offlinerl"},{"id":"2605.12771","title":"Adaptive Smooth Tchebycheff Attention for Multi-Objective Policy Optimization","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.20619","title":"SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.02221","title":"CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.03904","title":"MAdam: Metric-Aware Multi-Objective Adam","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.13169","title":"Redesigning Regularization for Effective Policy Smoothing","created":"2026-06-11","cited_by_count":0,"area":"deeprl"},{"id":"2607.01392","title":"Multi-Objective Exploration and Preference Optimization via Mutual Information","created":"2026-07-01","cited_by_count":0,"area":"alignment"},{"id":"2608.12704","title":"Efficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with Nonconvex Lower Level","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.13396","title":"Converge Then Diversify: Decoupling Convergence and Diversity in Multi-Objective Bayesian Optimisation","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.19858","title":"Expected Hypervolume Maximization for Multiobjective Optimization under Uncertainties","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.16840","title":"Few-for-Many Best-Arm Identification in Multi-Objective Bandits","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}