{"total":96,"rows":[{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823,"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":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040,"area":"moe"},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867,"area":"moe"},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428,"area":"moe"},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401,"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":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2601.02780","title":"MiMo-V2-Flash Technical Report","created":"2026-01-06","cited_by_count":191,"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":"2403.07652","title":"Harder Tasks Need More Experts: Dynamic Routing in MoE Models","created":"2024-03-12","cited_by_count":72,"area":"moe"},{"id":"2305.14705","title":"Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models","created":"2023-05-24","cited_by_count":65,"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":"2402.12656","title":"HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts","created":"2024-02-20","cited_by_count":26,"area":"moe"},{"id":"2511.00279","title":"LongCat-Flash-Omni Technical Report","created":"2025-10-31","cited_by_count":26,"area":"moe"},{"id":"2502.19261","title":"Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization","created":"2025-02-26","cited_by_count":24,"area":"moe"},{"id":"2406.12034","title":"Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts","created":"2024-06-17","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":"2406.11256","title":"Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts","created":"2024-06-17","cited_by_count":19,"area":"moe"},{"id":"2410.18035","title":"MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning","created":"2024-10-23","cited_by_count":19,"area":"moe"},{"id":"2411.12364","title":"Ultra-Sparse Memory Network","created":"2024-11-19","cited_by_count":19,"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":"2407.00256","title":"One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts","created":"2024-06-28","cited_by_count":16,"area":"moe"},{"id":"2410.10456","title":"Ada-K Routing: Boosting the Efficiency of MoE-based LLMs","created":"2024-10-14","cited_by_count":16,"area":"moe"},{"id":"2507.07024","title":"FlexOlmo: Open Language Models for Flexible Data Use","created":"2025-07-09","cited_by_count":15,"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":"2501.10375","title":"DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference","created":"2024-12-16","cited_by_count":14,"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":"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":"2407.21571","title":"PMoE: Progressive Mixture of Experts with Asymmetric Transformer for Continual Learning","created":"2024-07-31","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":"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":"2605.08738","title":"SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training","created":"2026-05-09","cited_by_count":7,"area":"moe"},{"id":"2410.01610","title":"Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging","created":"2024-10-02","cited_by_count":6,"area":"moe"},{"id":"2503.00634","title":"Efficiently Editing Mixture-of-Experts Models with Compressed Experts","created":"2025-03-01","cited_by_count":6,"area":"moe"},{"id":"2506.14646","title":"GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors","created":"2025-06-17","cited_by_count":6,"area":"moe"},{"id":"2505.15471","title":"CoLA: Collaborative Low-Rank Adaptation","created":"2025-05-21","cited_by_count":5,"area":"moe"},{"id":"2506.05767","title":"dots.llm1 Technical Report","created":"2025-06-06","cited_by_count":5,"area":"moe"},{"id":"2506.14436","title":"MoORE: SVD-based Model MoE-ization for Conflict- and Oblivion-Resistant Multi-Task Adaptation","created":"2025-06-17","cited_by_count":5,"area":"moe"},{"id":"2508.18756","title":"UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning","created":"2025-08-26","cited_by_count":5,"area":"moe"},{"id":"2605.15403","title":"$\\phi$-Balancing for Mixture-of-Experts Training","created":"2026-05-14","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":"2603.02217","title":"Is Retraining-Free Enough? The Necessity of Router Calibration for Efficient MoE Compression","created":"2026-02-10","cited_by_count":4,"area":"moe"},{"id":"2604.08133","title":"Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference","created":"2026-04-09","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":"2509.25689","title":"Collaborative Compression for Large-Scale MoE Deployment on Edge","created":"2025-09-30","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":"2602.00800","title":"JTok: On Token Embedding as another Axis of Scaling Law via Joint Token Self-modulation","created":"2026-01-31","cited_by_count":3,"area":"moe"},{"id":"2602.07616","title":"SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE Models","created":"2026-02-07","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":"2606.01062","title":"DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts","created":"2026-05-31","cited_by_count":3,"area":"moe"},{"id":"2408.17280","title":"Flexible and Effective Mixing of Large Language Models into a Mixture of Domain Experts","created":"2024-08-30","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":"2506.02965","title":"PC-MoE: Memory-Efficient and Privacy-Preserving Collaborative Training for Mixture-of-Experts LLMs","created":"2025-06-03","cited_by_count":1,"area":"moe"},{"id":"2512.03927","title":"OD-MoE: On-Demand Expert Loading for Cacheless Edge-Distributed MoE Inference","created":"2025-12-03","cited_by_count":1,"area":"moe"},{"id":"2604.18473","title":"Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts","created":"2026-04-20","cited_by_count":1,"area":"moe"},{"id":"2609.40316","title":"Scaling Laws for Looped Mixture of Experts","created":"2026-09-30","cited_by_count":1,"area":"moe"},{"id":"2509.10530","title":"Dynamic Adaptive Shared Experts with Grouped Multi-Head Attention Mixture of Experts","created":"2025-09-05","cited_by_count":0,"area":"moe"},{"id":"2602.05711","title":"OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale","created":"2026-02-05","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":"2603.13364","title":"FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach","created":"2026-03-09","cited_by_count":0,"area":"moe"},{"id":"2605.26496","title":"Dense2MoE: Pushing the Pareto Frontier of On-Device LLMs via Unified Pruning and Upcycling","created":"2026-05-26","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":"2606.12397","title":"Redesign Mixture-of-Experts Routers with Manifold Power Iteration","created":"2026-06-10","cited_by_count":0,"area":"moe"},{"id":"2607.00293","title":"Rosetta: Composable Native Multimodal Pretraining","created":"2026-07-01","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":"2608.20061","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":"2608.30567","title":"TuringLLM: Efficiently Scaling Foundation Models Toward Physical AI","created":"2026-08-31","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":"2609.06076","title":"Beyond Retraining-Free MoE Compression: A Cost-Normalized Study of Post-Compression Adjustment","created":"2026-09-05","cited_by_count":0,"area":"moe"},{"id":"2609.20974","title":"Attention-Aware Routing: Coupling Routing and Attention in MoEs","created":"2026-09-17","cited_by_count":0,"area":"moe"},{"id":"2609.21672","title":"Accelerating Dense LLMs via L0-regularized Mixture-of-Experts","created":"2026-09-18","cited_by_count":0,"area":"moe"},{"id":"2609.22199","title":"Improving Parameter Utilization by Sharing Neural Experts Across Layers in Transformers","created":"2026-08-31","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":"2609.31631","title":"OMP-MoE: Efficient Expert Pruning for Mixture-of-Experts LLMs via Orthogonal Matching Pursuit","created":"2026-09-09","cited_by_count":0,"area":"moe"},{"id":"2609.36222","title":"BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding","created":"2026-09-28","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":"2610.04473","title":"InferOpt: Constrained Multi-Objective Search for LLM Inference Configurations","created":"2026-10-03","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":"2610.11317","title":"DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition","created":"2026-10-08","cited_by_count":0,"area":"moe"},{"id":"2610.11575","title":"Smoothing the Top-k Exposure Boundary for Sparse Mixture-of-Experts","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}