{"total":73,"rows":[{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942,"area":"moe"},{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040,"area":"moe"},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428,"area":"moe"},{"id":"2601.02780","title":"MiMo-V2-Flash Technical Report","created":"2026-01-06","cited_by_count":191,"area":"moe"},{"id":"2604.15804","title":"Qwen3.5-Omni Technical Report","created":"2026-04-17","cited_by_count":174,"area":"moe"},{"id":"2411.02265","title":"Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent","created":"2024-11-04","cited_by_count":90,"area":"moe"},{"id":"2601.07372","title":"Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models","created":"2026-01-12","cited_by_count":86,"area":"moe"},{"id":"2508.15763","title":"Intern-S1: A Scientific Multimodal Foundation Model","created":"2025-08-21","cited_by_count":53,"area":"moe"},{"id":"2507.17702","title":"Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language Models","created":"2025-07-23","cited_by_count":45,"area":"moe"},{"id":"2505.22323","title":"Advancing Expert Specialization for Better MoE","created":"2025-05-28","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":"2608.30320","title":"On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability","created":"2026-08-31","cited_by_count":35,"area":"moe"},{"id":"2511.00279","title":"LongCat-Flash-Omni Technical Report","created":"2025-10-31","cited_by_count":26,"area":"moe"},{"id":"2505.23854","title":"Revisiting Uncertainty Estimation and Calibration of Large Language Models","created":"2025-05-29","cited_by_count":23,"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":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21,"area":"moe"},{"id":"2505.21411","title":"Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity","created":"2025-05-27","cited_by_count":18,"area":"moe"},{"id":"2601.21204","title":"Scaling Embeddings Outperforms Scaling Experts in Language Models","created":"2026-01-29","cited_by_count":15,"area":"moe"},{"id":"2605.23872","title":"Training-Free Looped Transformers","created":"2026-05-22","cited_by_count":15,"area":"moe"},{"id":"2510.10302","title":"SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference","created":"2025-10-11","cited_by_count":13,"area":"moe"},{"id":"2505.04519","title":"Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs","created":"2025-05-07","cited_by_count":12,"area":"moe"},{"id":"2512.23447","title":"Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss","created":"2025-12-29","cited_by_count":11,"area":"moe"},{"id":"2602.04705","title":"ERNIE 5.0 Technical Report","created":"2026-02-04","cited_by_count":11,"area":"moe"},{"id":"2602.17004","title":"Arcee Trinity Large Technical Report","created":"2026-02-19","cited_by_count":11,"area":"moe"},{"id":"2602.03560","title":"HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing","created":"2026-02-03","cited_by_count":10,"area":"moe"},{"id":"2508.07785","title":"Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts","created":"2025-08-11","cited_by_count":9,"area":"moe"},{"id":"2506.09440","title":"GigaChat Family: Efficient Russian Language Modeling Through Mixture of Experts Architecture","created":"2025-06-11","cited_by_count":8,"area":"moe"},{"id":"2506.12119","title":"Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource","created":"2025-06-13","cited_by_count":8,"area":"moe"},{"id":"2508.12851","title":"Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement","created":"2025-08-18","cited_by_count":7,"area":"moe"},{"id":"2511.15015","title":"Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference","created":"2025-11-19","cited_by_count":7,"area":"moe"},{"id":"2602.07265","title":"XShare: Collaborative in-Batch Expert Sharing for Faster MoE Inference","created":"2026-02-06","cited_by_count":7,"area":"moe"},{"id":"2510.05497","title":"Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference","created":"2025-10-07","cited_by_count":6,"area":"moe"},{"id":"2606.05688","title":"Value-and-Structure Alignment for Routing-Consistent Quantization of Mixture-of-Experts Models","created":"2026-06-04","cited_by_count":6,"area":"moe"},{"id":"2506.05767","title":"dots.llm1 Technical Report","created":"2025-06-06","cited_by_count":5,"area":"moe"},{"id":"2601.02967","title":"MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free","created":"2026-01-06","cited_by_count":5,"area":"moe"},{"id":"2603.09983","title":"MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios","created":"2026-02-12","cited_by_count":5,"area":"moe"},{"id":"2606.26560","title":"Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention","created":"2026-06-25","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":"2605.06663","title":"EMO: Pretraining Mixture of Experts for Emergent Modularity","created":"2026-05-07","cited_by_count":4,"area":"moe"},{"id":"2605.24956","title":"NITP: Next Implicit Token Prediction for LLM Pre-training","created":"2026-05-24","cited_by_count":4,"area":"moe"},{"id":"2607.14530","title":"xHC: Expanded Hyper-Connections","created":"2026-07-16","cited_by_count":4,"area":"moe"},{"id":"2509.10513","title":"Mixture-of-Clustered-Experts: Advancing Expert Specialization and Generalization in Instruction Tuning","created":"2025-09-03","cited_by_count":3,"area":"moe"},{"id":"2601.21420","title":"ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation","created":"2026-01-29","cited_by_count":3,"area":"moe"},{"id":"2604.19048","title":"SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning","created":"2026-04-21","cited_by_count":3,"area":"moe"},{"id":"2605.27358","title":"MobileMoE: Scaling On-Device Mixture of Experts","created":"2026-05-26","cited_by_count":3,"area":"moe"},{"id":"2506.00965","title":"FLEx: Personalized Federated Learning for Mixture-of-Experts LLMs via Expert Grafting","created":"2025-06-01","cited_by_count":2,"area":"moe"},{"id":"2510.13079","title":"GatePro: Parameter-Free Expert Selection Optimization for Mixture-of-Experts Models","created":"2025-10-15","cited_by_count":2,"area":"moe"},{"id":"2512.16248","title":"Sigma-MoE-Tiny Technical Report","created":"2025-12-18","cited_by_count":2,"area":"moe"},{"id":"2601.07022","title":"Solar Open Technical Report","created":"2026-01-11","cited_by_count":2,"area":"moe"},{"id":"2608.24938","title":"ExFold: Unified Expert Folding for Training-Free MoE Prefill-Decode Acceleration","created":"2026-08-24","cited_by_count":2,"area":"moe"},{"id":"2601.09200","title":"A.X K1 Technical Report","created":"2026-01-14","cited_by_count":0,"area":"moe"},{"id":"2602.08818","title":"FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models","created":"2026-02-09","cited_by_count":0,"area":"moe"},{"id":"2604.05267","title":"Do Domain-specific Experts exist in MoE-based LLMs?","created":"2026-04-07","cited_by_count":0,"area":"moe"},{"id":"2605.25698","title":"How Should LLMs Consume High-Quality Data? Optimal Data Scheduling via Quality-Aware Functional Scaling Laws","created":"2026-05-25","cited_by_count":0,"area":"moe"},{"id":"2605.26842","title":"MONA: Muon Optimizer with Nesterov Acceleration for Scalable Language Model Training","created":"2026-05-26","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":"2608.04505","title":"K-EXAONE 2.0 Technical Report","created":"2026-08-05","cited_by_count":0,"area":"moe"},{"id":"2608.07890","title":"Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models","created":"2026-08-08","cited_by_count":0,"area":"moe"},{"id":"2608.09119","title":"Motif 3: Technical Report","created":"2026-08-10","cited_by_count":0,"area":"moe"},{"id":"2608.20061","title":"Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts","created":"2026-08-20","cited_by_count":0,"area":"moe"},{"id":"2608.28511","title":"Training Communication-Efficient Mixture-of-Experts Language Models with Layer Re-Configuration","created":"2026-08-28","cited_by_count":0,"area":"moe"},{"id":"2608.30567","title":"TuringLLM: Efficiently Scaling Foundation Models Toward Physical AI","created":"2026-08-31","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":"2609.14643","title":"BigMoMo: Efficient Inference of Large-Scale MoE with Speculative Decoding on Mobile Devices","created":"2026-09-13","cited_by_count":0,"area":"moe"},{"id":"2609.25809","title":"You Only Need 2/3 of the Chosen Experts: An Empirical Study of Dynamic Expert Pruning in Fine-Grained MoE LLMs","created":"2026-09-22","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":"2609.32398","title":"Function Over Form: Distributional Orthogonalization in Mixture-of-Experts with Replica Expert Mechanism","created":"2026-09-26","cited_by_count":0,"area":"moe"},{"id":"2609.39137","title":"ID Balancing: Stable Training of Extremely Sparse MoE via PID-Based Load Control","created":"2026-09-30","cited_by_count":0,"area":"moe"},{"id":"2610.05744","title":"CIPHER-MoE: Balancing Efficiency and Routing Fidelity in Trillion-Scale MoE Training","created":"2026-10-05","cited_by_count":0,"area":"moe"},{"id":"2610.12582","title":"One Model to Loop Them All: Elastic Latent Recurrence for Language Models","created":"2026-10-08","cited_by_count":0,"area":"moe"},{"id":"2610.14074","title":"One Model, Multiple Compute Budgets: Multi-Ratio ConceptMoE for Flexible Compute Across Turns","created":"2026-10-08","cited_by_count":0,"area":"moe"},{"id":"2610.17959","title":"Virtual Head Attention","created":"2026-10-13","cited_by_count":0,"area":"moe"}],"next_cursor":null}