{"total":44,"rows":[{"id":"2507.18071","title":"Group Sequence Policy Optimization","created":"2025-07-24","cited_by_count":835,"area":"moe"},{"id":"2601.02780","title":"MiMo-V2-Flash Technical Report","created":"2026-01-06","cited_by_count":191,"area":"moe"},{"id":"2503.07137","title":"A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications","created":"2025-03-10","cited_by_count":91,"area":"moe"},{"id":"2510.11370","title":"Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers","created":"2025-10-13","cited_by_count":72,"area":"moe"},{"id":"2512.01374","title":"Stabilizing Reinforcement Learning with LLMs: Formulation and Practices","created":"2025-12-01","cited_by_count":41,"area":"moe"},{"id":"2505.09343","title":"Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures","created":"2025-05-14","cited_by_count":39,"area":"moe"},{"id":"2104.09122","title":"Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning","created":"2021-04-19","cited_by_count":27,"area":"moe"},{"id":"2503.08564","title":"MoE-Loco: Mixture of Experts for Multitask Locomotion","created":"2025-03-11","cited_by_count":23,"area":"moe"},{"id":"2406.18420","title":"Mixture of Experts in a Mixture of RL settings","created":"2024-06-26","cited_by_count":21,"area":"moe"},{"id":"2607.07675","title":"Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence","created":"2026-07-08","cited_by_count":15,"area":"moe"},{"id":"2403.06966","title":"Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts","created":"2024-03-11","cited_by_count":14,"area":"moe"},{"id":"2506.10357","title":"Optimus-3: Dual-Router Aligned Mixture-of-Experts Agent with Dual-Granularity Reasoning-Aware Policy Optimization","created":"2025-06-12","cited_by_count":13,"area":"moe"},{"id":"2411.00782","title":"TradExpert: Revolutionizing Trading with Mixture of Expert LLMs","created":"2024-10-16","cited_by_count":12,"area":"moe"},{"id":"2602.10693","title":"VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training","created":"2026-02-11","cited_by_count":11,"area":"moe"},{"id":"2410.02475","title":"Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping","created":"2024-10-03","cited_by_count":10,"area":"moe"},{"id":"2506.05426","title":"Mixture-of-Experts Meets In-Context Reinforcement Learning","created":"2025-06-05","cited_by_count":8,"area":"moe"},{"id":"2302.00586","title":"PRUDEX-Compass: Towards Systematic Evaluation of Reinforcement Learning in Financial Markets","created":"2023-01-14","cited_by_count":5,"area":"moe"},{"id":"2607.18722","title":"Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning","created":"2026-07-21","cited_by_count":5,"area":"moe"},{"id":"2504.09906","title":"Plasticity-Aware Mixture of Experts for Learning Under QoE Shifts in Adaptive Video Streaming","created":"2025-04-14","cited_by_count":4,"area":"moe"},{"id":"2011.10605","title":"Nested Mixture of Experts: Cooperative and Competitive Learning of Hybrid Dynamical System","created":"2020-11-20","cited_by_count":3,"area":"moe"},{"id":"2502.05633","title":"Mol-MoE: Training Preference-Guided Routers for Molecule Generation","created":"2025-02-08","cited_by_count":3,"area":"moe"},{"id":"2507.09955","title":"DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models","created":"2025-07-14","cited_by_count":3,"area":"moe"},{"id":"2604.25578","title":"Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient Upcycling","created":"2026-04-28","cited_by_count":3,"area":"moe"},{"id":"2605.08639","title":"ReLibra: Routing-Replay-Guided Load Balancing for MoE Training in Reinforcement Learning","created":"2026-05-09","cited_by_count":3,"area":"moe"},{"id":"2607.15810","title":"QUADS: Stabilizing NVFP4 Reinforcement Learning for MoE via QUantization-error Alignment across Dual Sides","created":"2026-07-17","cited_by_count":3,"area":"moe"},{"id":"1803.02493","title":"Discontinuity-Sensitive Optimal Control Learning by Mixture of Experts","created":"2018-03-07","cited_by_count":2,"area":"moe"},{"id":"2606.11867","title":"Harnessing Routing Foresight for Micro-step-level MoE load balancing in RL Post-training","created":"2026-06-10","cited_by_count":2,"area":"moe"},{"id":"2606.30997","title":"A Three-Phase Foundation Model for Tax-Aware Personalized Portfolio Management","created":"2026-06-30","cited_by_count":2,"area":"moe"},{"id":"2503.06413","title":"Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models","created":"2025-03-09","cited_by_count":1,"area":"moe"},{"id":"2507.09836","title":"Multi-residual Mixture of Experts Learning for Cooperative Control in Multi-vehicle Systems","created":"2025-07-14","cited_by_count":1,"area":"moe"},{"id":"2604.03044","title":"JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency","created":"2026-04-03","cited_by_count":1,"area":"moe"},{"id":"2604.09028","title":"Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networks","created":"2026-04-10","cited_by_count":1,"area":"moe"},{"id":"2606.00395","title":"PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning","created":"2026-05-29","cited_by_count":1,"area":"moe"},{"id":"2607.20145","title":"SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD","created":"2026-07-22","cited_by_count":1,"area":"moe"},{"id":"2501.13994","title":"CSAOT: Cooperative Multi-Agent System for Active Object Tracking","created":"2025-01-23","cited_by_count":0,"area":"moe"},{"id":"2511.18987","title":"Dynamic Mixture of Experts Against Severe Distribution Shifts","created":"2025-11-24","cited_by_count":0,"area":"moe"},{"id":"2512.13727","title":"RAST-MoE-RL: A Regime-Aware Spatio-Temporal MoE Framework for Deep Reinforcement Learning in Ride-Hailing","created":"2025-12-13","cited_by_count":0,"area":"moe"},{"id":"2512.14712","title":"SepsisSuite: Beyond Risk Stratification -- A Comparative Analysis of Deep Fusion vs. Expert Stacking for Prescriptive Sepsis AI","created":"2025-12-08","cited_by_count":0,"area":"moe"},{"id":"2606.04718","title":"CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptation","created":"2026-06-03","cited_by_count":0,"area":"moe"},{"id":"2606.09038","title":"Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs","created":"2026-06-08","cited_by_count":0,"area":"moe"},{"id":"2606.19633","title":"CTS-MoE: Implicit Terrain Adaptation via Mixture-of-Experts for Perceptive Locomotion","created":"2026-06-17","cited_by_count":0,"area":"moe"},{"id":"2607.23070","title":"DishSeg24k: A Large-Scale Benchmark for Food Segmentation with Stochastic Expert Decoding","created":"2026-07-25","cited_by_count":0,"area":"moe"},{"id":"2609.00284","title":"WiSDoM: Wireless Sparse Decision Transformer with Mixture-of-Experts for Multi-Task Mobile Network Optimization","created":"2026-08-31","cited_by_count":0,"area":"moe"},{"id":"2610.18010","title":"Fish Audio Drama 3 Technical Report","created":"2026-10-13","cited_by_count":0,"area":"moe"}],"next_cursor":null}