{"total":43,"rows":[{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942,"area":"moe"},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135,"area":"moe"},{"id":"2507.18071","title":"Group Sequence Policy Optimization","created":"2025-07-24","cited_by_count":835,"area":"moe"},{"id":"2406.11931","title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","created":"2024-06-17","cited_by_count":331,"area":"moe"},{"id":"2601.02780","title":"MiMo-V2-Flash Technical Report","created":"2026-01-06","cited_by_count":191,"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":"2508.15763","title":"Intern-S1: A Scientific Multimodal Foundation Model","created":"2025-08-21","cited_by_count":53,"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":"2505.12082","title":"Model Merging in Pre-training of Large Language Models","created":"2025-05-17","cited_by_count":37,"area":"moe"},{"id":"2503.05139","title":"Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs","created":"2025-03-07","cited_by_count":22,"area":"moe"},{"id":"2510.24821","title":"Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation","created":"2025-10-28","cited_by_count":22,"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":"2503.17793","title":"Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM","created":"2025-03-22","cited_by_count":13,"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":"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":"2410.00938","title":"MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards","created":"2024-10-01","cited_by_count":7,"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":"2507.18671","title":"Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling","created":"2025-07-24","cited_by_count":4,"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":"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":"2609.07549","title":"Qwen-Audio-3.0-ASR Technical Report","created":"2026-09-07","cited_by_count":2,"area":"moe"},{"id":"2512.07135","title":"TrajMoE: Scene-Adaptive Trajectory Planning with Mixture of Experts and Reinforcement Learning","created":"2025-12-08","cited_by_count":1,"area":"moe"},{"id":"2604.01152","title":"Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning","created":"2026-04-01","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":"2605.21951","title":"Dynamic Mixture of Latent Memories for Self-Evolving Agents","created":"2026-05-21","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":"2606.26607","title":"Moebius: Serving Mixture-of-Expert Models with Seamless Runtime Parallelism Switch","created":"2026-06-25","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":"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":"2605.31268","title":"Mellum2 Technical Report","created":"2026-05-29","cited_by_count":0,"area":"moe"},{"id":"2606.10369","title":"PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning","created":"2026-06-09","cited_by_count":0,"area":"moe"},{"id":"2608.10823","title":"MoE Proxy Models for Low-Cost Failure Reproduction and Diagnosis in LLM RL Post-Training","created":"2026-08-11","cited_by_count":0,"area":"moe"},{"id":"2608.12146","title":"RoutePack: Expert Placement and Attention-Aware Data Packing for MoE Reinforcement Learning","created":"2026-08-12","cited_by_count":0,"area":"moe"},{"id":"2608.17744","title":"Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See","created":"2026-08-18","cited_by_count":0,"area":"moe"},{"id":"2609.00791","title":"Instella-MoE Technical Report","created":"2026-09-01","cited_by_count":0,"area":"moe"},{"id":"2609.08663","title":"MoEMB: Scaling Universal Multimodal Embeddings with Efficient Mixture-of-Experts Models","created":"2026-09-08","cited_by_count":0,"area":"moe"},{"id":"2609.13058","title":"Expert-Space Exploration in MoE Reinforcement Learning","created":"2026-09-11","cited_by_count":0,"area":"moe"},{"id":"2609.27284","title":"Hunyuan-A13B Technical Report","created":"2026-09-23","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}