{"total":99,"rows":[{"id":"2406.03949","title":"UltraMedical: Building Specialized Generalists in Biomedicine","created":"2024-06-06","cited_by_count":67,"area":null},{"id":"2602.03139","title":"Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis","created":"2026-02-03","cited_by_count":20,"area":null},{"id":"2409.09892","title":"Dynamic Fraud Detection: Integrating Reinforcement Learning into Graph Neural Networks","created":"2024-09-15","cited_by_count":19,"area":null},{"id":"2510.06077","title":"When Thinking Drifts: Evidential Grounding for Robust Video Reasoning","created":"2025-10-07","cited_by_count":16,"area":null},{"id":"2406.14096","title":"Graph Neural Networks for Job Shop Scheduling Problems: A Survey","created":"2024-06-20","cited_by_count":15,"area":null},{"id":"2405.16236","title":"A transfer learning framework for weak-to-strong generalization","created":"2024-05-25","cited_by_count":14,"area":null},{"id":"2412.08845","title":"Quantum-Train-Based Distributed Multi-Agent Reinforcement Learning","created":"2024-12-12","cited_by_count":14,"area":null},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2508.13514","title":"ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs","created":"2025-08-19","cited_by_count":13,"area":null},{"id":"2406.15609","title":"Automated radiotherapy treatment planning guided by GPT-4Vision","created":"2024-06-21","cited_by_count":12,"area":null},{"id":"2504.08751","title":"Research on the Design of a Short Video Recommendation System Based on Multimodal Information and Differential Privacy","created":"2025-03-27","cited_by_count":9,"area":null},{"id":"2505.06305","title":"User Behavior Analysis in Privacy Protection with Large Language Models: A Study on Privacy Preferences with Limited Data","created":"2025-05-08","cited_by_count":8,"area":null},{"id":"2406.19765","title":"Systematic Literature Review on Application of Learning-based Approaches in Continuous Integration","created":"2024-06-28","cited_by_count":6,"area":null},{"id":"2411.16797","title":"Enhancing Answer Reliability Through Inter-Model Consensus of Large Language Models","created":"2024-11-25","cited_by_count":6,"area":null},{"id":"2408.05860","title":"Root Cause Attribution of Delivery Risks via Causal Discovery with Reinforcement Learning","created":"2024-08-11","cited_by_count":5,"area":null},{"id":"2410.04811","title":"Learning Efficient and Effective Trajectories for Differential Equation-based Image Restoration","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2410.16655","title":"Memory-Efficient Large Language Models for Program Repair with Semantic-Guided Patch Generation","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2504.01766","title":"Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2601.05187","title":"SimuAgent: An LLM-Based Simulink Modeling Assistant Enhanced with Reinforcement Learning","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2409.02349","title":"Machine Learning Applications to Computational Plasma Physics and Reduced-Order Plasma Modeling: A Perspective","created":"2024-09-04","cited_by_count":4,"area":null},{"id":"2410.05406","title":"Synthesizing Interpretable Control Policies through Large Language Model Guided Search","created":"2024-10-07","cited_by_count":4,"area":null},{"id":"2411.13945","title":"Neuromorphic Attitude Estimation and Control","created":"2024-11-21","cited_by_count":4,"area":null},{"id":"2602.12394","title":"Synthetic Interaction Data for Scalable Personalization in Large Language Models","created":"2026-02-12","cited_by_count":4,"area":null},{"id":"2407.05336","title":"Artificial intelligence, rationalization, and the limits of control in the public sector: the case of tax policy optimization","created":"2024-07-07","cited_by_count":3,"area":null},{"id":"2503.15726","title":"Reinforcement Learning Environment with LLM-Controlled Adversary in D&D 5th Edition Combat","created":"2025-03-19","cited_by_count":3,"area":null},{"id":"2505.07089","title":"RefPentester: A Knowledge-Informed Self-Reflective Penetration Testing Framework Based on Large Language Models","created":"2025-05-11","cited_by_count":3,"area":null},{"id":"2511.05120","title":"A Toolbox for Improving Evolutionary Prompt Search","created":"2025-11-07","cited_by_count":3,"area":null},{"id":"2410.07368","title":"Learning to learn ecosystems from limited data -- a meta-learning approach","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2503.04803","title":"An energy-efficient learning solution for the Agile Earth Observation Satellite Scheduling Problem","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2505.12107","title":"Learning Probabilistic Temporal Logic Specifications for Stochastic Systems","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2505.14938","title":"Scan, Materialize, Simulate: A Generalizable Framework for Physically Grounded Robot Planning","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2510.10066","title":"OBsmith: LLM-Powered JavaScript Obfuscator Testing","created":"2025-10-11","cited_by_count":2,"area":null},{"id":"2512.09485","title":"Advancing LLM-Based Security Automation with Customized Group Relative Policy Optimization for Zero-Touch Networks","created":"2025-12-10","cited_by_count":2,"area":null},{"id":"2602.01427","title":"Robust Generalization with Adaptive Optimal Transport Priors for Decision-Focused Learning","created":"2026-02-01","cited_by_count":2,"area":null},{"id":"2603.17145","title":"REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2405.18823","title":"Why Reinforcement Learning in Energy Systems Needs Explanations","created":"2024-05-29","cited_by_count":1,"area":null},{"id":"2410.15250","title":"Multi-modal Policies with Physics-informed Representations in Complex Fluid Environments","created":"2024-10-20","cited_by_count":1,"area":null},{"id":"2410.15601","title":"All You Need is an Improving Column: Enhancing Column Generation for Parallel Machine Scheduling via Transformers","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2507.10142","title":"Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2508.03094","title":"Augmenting Continual Learning of Diseases with LLM-Generated Visual Concepts","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2511.05872","title":"Adaptation and Fine-tuning with TabPFN for Travelling Salesman Problem","created":"2025-11-08","cited_by_count":1,"area":null},{"id":"2511.14768","title":"Causally-Informed Reinforcement Learning for Adaptive Emotion-Aware Social Media Recommendation","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2601.00105","title":"Mortar: Evolving Mechanics for Automatic Game Design","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2601.01060","title":"Unsupervised Text Style Transfer for Controllable Intensity","created":"2026-01-03","cited_by_count":1,"area":null},{"id":"2602.03466","title":"Quantum Circuit Generation via test-time learning with large language models","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.23249","title":"A Learning Method with Gap-Aware Generation for Heterogeneous DAG Scheduling","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.12319","title":"RSGMamba: Reliability-Aware Self-Gated State Space Model for Multimodal Semantic Segmentation","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2607.17290","title":"Lookahead Branching for Neural Network Verification","created":"2026-07-19","cited_by_count":1,"area":null},{"id":"2607.17768","title":"To Blend In, First Decouple: Rethinking Camouflage Image Generation via Context-Decoupled Representations","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2405.13130","title":"Pure Planning to Pure Policies and In Between with a Recursive Tree Planner","created":"2024-05-21","cited_by_count":0,"area":null},{"id":"2405.15975","title":"Inference of Utilities and Time Preference in Sequential Decision-Making","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2405.16610","title":"The devil is in discretization discrepancy. Robustifying Differentiable NAS with Single-Stage Searching Protocol","created":"2024-05-26","cited_by_count":0,"area":null},{"id":"2405.16994","title":"Vision-and-Language Navigation Generative Pretrained Transformer","created":"2024-05-27","cited_by_count":0,"area":null},{"id":"2406.14004","title":"Do Not Wait: Learning Re-Ranking Model Without User Feedback At Serving Time in E-Commerce","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2406.16748","title":"OCALM: Object-Centric Assessment with Language Models","created":"2024-06-24","cited_by_count":0,"area":null},{"id":"2407.06507","title":"Economic span selection of bridge based on deep reinforcement learning","created":"2024-07-09","cited_by_count":0,"area":null},{"id":"2407.08324","title":"A Cantor-Kantorovich Metric Between Markov Decision Processes with Application to Transfer Learning","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2408.08059","title":"Maximally Permissive Reward Machines","created":"2024-08-15","cited_by_count":0,"area":null},{"id":"2409.13571","title":"Scalable Multi-agent Reinforcement Learning for Factory-wide Dynamic Scheduling","created":"2024-09-20","cited_by_count":0,"area":null},{"id":"2410.01871","title":"Auction-Based Regulation for Artificial Intelligence","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2410.09186","title":"AI Learning Algorithms: Deep Learning, Hybrid Models, and Large-Scale Model Integration","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2411.03131","title":"Machine Learning Innovations in CPR: A Comprehensive Survey on Enhanced Resuscitation Techniques","created":"2024-11-03","cited_by_count":0,"area":null},{"id":"2412.10892","title":"Know Unreported Roadway Incidents in Real-time: Early Traffic Anomaly Detection","created":"2024-12-14","cited_by_count":0,"area":null},{"id":"2412.20279","title":"Deep Generalized Schr\\\"odinger Bridges: From Image Generation to Solving Mean-Field Games","created":"2024-12-28","cited_by_count":0,"area":null},{"id":"2501.06376","title":"Robustness in the Face of Partial Identifiability in Reward Learning","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2501.10243","title":"Random-Key Algorithms for Optimizing Integrated Operating Room Scheduling","created":"2025-01-17","cited_by_count":0,"area":null},{"id":"2502.12834","title":"NTP-INT: Network Traffic Prediction-Driven In-band Network Telemetry for High-load Switches","created":"2025-02-18","cited_by_count":0,"area":null},{"id":"2503.22779","title":"Policy Optimization and Multi-agent Reinforcement Learning for Mean-variance Team Stochastic Games","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2503.23491","title":"POINT$^{2}$: A Polymer Informatics Training and Testing Database","created":"2025-03-30","cited_by_count":0,"area":null},{"id":"2505.02853","title":"A Computational Model of Inclusive Pedagogy: From Understanding to Application","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2505.06706","title":"Bi-level Mean Field: Dynamic Grouping for Large-Scale MARL","created":"2025-05-10","cited_by_count":0,"area":null},{"id":"2506.16822","title":"Learning Dexterous Object Handover","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2507.02634","title":"High-Order Deep Meta-Learning with Category-Theoretic Interpretation","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2507.19663","title":"Adaptive Bayesian Data-Driven Design of Reliable Solder Joints for Micro-electronic Devices","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2508.13661","title":"Communication-Enhanced Tutoring for Efficient Decentralized Multi-Agent Reinforcement Learning","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2508.13703","title":"Minimizing the Weighted Number of Tardy Jobs: Data-Driven Heuristic for Single-Machine Scheduling","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2509.05890","title":"Quantum spatial best-arm identification via quantum walks","created":"2025-09-07","cited_by_count":0,"area":null},{"id":"2509.07633","title":"Variational Quantum Circuits in Offline Contextual Bandit Problems","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2509.19695","title":"DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual-Systems","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.01020","title":"The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.08763","title":"Reinforcement Learning-Based Optimization of CT Acquisition and Reconstruction Parameters Through Virtual Imaging Trials","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2510.12555","title":"Inclusive Fitness as a Key Step Towards More Advanced Social Behaviors in Multi-Agent Reinforcement Learning Settings","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2510.18431","title":"ScaleNet: Scaling up Pretrained Neural Networks with Incremental Parameters","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2510.27145","title":"Relation-Aware Bayesian Optimization of DBMS Configurations Guided by Affinity Scores","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2511.03586","title":"PerfDojo: Automated ML Library Generation for Heterogeneous Architectures","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2511.21934","title":"Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2512.17918","title":"QAISim: A Toolkit for Modeling and Simulation of AI in Quantum Cloud Computing Environments","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2601.03451","title":"Microeconomic Foundations of Multi-Agent Learning","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.04269","title":"Systems Explaining Systems: A Framework for Intelligence and Consciousness","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2602.00580","title":"Small Shifts, Large Gains: Unlocking Traditional TSP Heuristic Guided-Sampling via Unsupervised Neural Instance Modification","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.22786","title":"QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.16350","title":"Explainable machine learning workflows for radio astronomical data processing","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2606.04845","title":"Bayesian learning for the stochastic shortest path problem","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.24990","title":"Uncertainty-aware reinforcement learning for chemical language models","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.17149","title":"A Diagnostic Framework for AI Agent Behavior","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2608.04255","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.11239","title":"Reinforcement Learning based DBMS Buffer Pool Auto-Tuning for Optimal Memory Utilization","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.35259","title":"On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.13737","title":"SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}