{"total":255,"rows":[{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942,"area":"moe"},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401,"area":"moe"},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283,"area":"moe"},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237,"area":"moe"},{"id":"2206.02770","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts","created":"2022-06-06","cited_by_count":203,"area":"moe"},{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"id":"2402.01739","title":"OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models","created":"2024-01-29","cited_by_count":187,"area":"moe"},{"id":"2309.05444","title":"Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning","created":"2023-09-11","cited_by_count":150,"area":"moe"},{"id":"2404.15159","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","created":"2024-04-22","cited_by_count":147,"area":"moe"},{"id":"2410.05993","title":"Aria: An Open Multimodal Native Mixture-of-Experts Model","created":"2024-10-08","cited_by_count":138,"area":"moe"},{"id":"2406.16554","title":"LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training","created":"2024-06-24","cited_by_count":123,"area":"moe"},{"id":"2402.08562","title":"Higher Layers Need More LoRA Experts","created":"2024-02-13","cited_by_count":102,"area":"moe"},{"id":"2305.13230","title":"To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis","created":"2023-05-22","cited_by_count":92,"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":"2309.14393","title":"LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models","created":"2023-09-25","cited_by_count":72,"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":"2402.11260","title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","created":"2024-02-17","cited_by_count":63,"area":"moe"},{"id":"2412.14711","title":"ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing","created":"2024-12-19","cited_by_count":54,"area":"moe"},{"id":"2501.11873","title":"Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models","created":"2025-01-21","cited_by_count":54,"area":"moe"},{"id":"2304.03946","title":"FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement","created":"2023-04-08","cited_by_count":53,"area":"moe"},{"id":"2501.12370","title":"Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models","created":"2025-01-21","cited_by_count":50,"area":"moe"},{"id":"2410.07524","title":"Upcycling Large Language Models into Mixture of Experts","created":"2024-10-10","cited_by_count":49,"area":"moe"},{"id":"2406.18219","title":"A Closer Look into Mixture-of-Experts in Large Language Models","created":"2024-06-26","cited_by_count":48,"area":"moe"},{"id":"2409.03277","title":"ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding","created":"2024-09-05","cited_by_count":46,"area":"moe"},{"id":"2310.16795","title":"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models","created":"2023-10-25","cited_by_count":42,"area":"moe"},{"id":"2404.05089","title":"SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts","created":"2024-04-07","cited_by_count":40,"area":"moe"},{"id":"2505.22323","title":"Advancing Expert Specialization for Better MoE","created":"2025-05-28","cited_by_count":39,"area":"moe"},{"id":"2405.03133","title":"Lory: Fully Differentiable Mixture-of-Experts for Autoregressive Language Model Pre-training","created":"2024-05-06","cited_by_count":37,"area":"moe"},{"id":"2407.09590","title":"Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts","created":"2024-07-12","cited_by_count":37,"area":"moe"},{"id":"2404.05019","title":"Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts","created":"2024-04-07","cited_by_count":32,"area":"moe"},{"id":"2502.07972","title":"Training Sparse Mixture Of Experts Text Embedding Models","created":"2025-02-11","cited_by_count":32,"area":"moe"},{"id":"2502.05172","title":"Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient","created":"2025-02-07","cited_by_count":31,"area":"moe"},{"id":"2507.13575","title":"Apple Intelligence Foundation Language Models: Tech Report 2025","created":"2025-07-17","cited_by_count":28,"area":"moe"},{"id":"2211.10017","title":"Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production","created":"2022-11-18","cited_by_count":27,"area":"moe"},{"id":"2506.14038","title":"Load Balancing Mixture of Experts with Similarity Preserving Routers","created":"2025-06-16","cited_by_count":22,"area":"moe"},{"id":"2408.06793","title":"Layerwise Recurrent Router for Mixture-of-Experts","created":"2024-08-13","cited_by_count":21,"area":"moe"},{"id":"2410.19034","title":"Mixture of Parrots: Experts improve memorization more than reasoning","created":"2024-10-24","cited_by_count":21,"area":"moe"},{"id":"2402.13089","title":"Towards an empirical understanding of MoE design choices","created":"2024-02-20","cited_by_count":20,"area":"moe"},{"id":"2410.10054","title":"AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality","created":"2024-10-14","cited_by_count":20,"area":"moe"},{"id":"2504.05586","title":"Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations","created":"2025-04-08","cited_by_count":20,"area":"moe"},{"id":"2405.14507","title":"Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast","created":"2024-05-23","cited_by_count":19,"area":"moe"},{"id":"2603.07685","title":"Scalable Training of Mixture-of-Experts Models with Megatron Core","created":"2026-03-08","cited_by_count":19,"area":"moe"},{"id":"2312.10868","title":"From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape","created":"2023-12-18","cited_by_count":18,"area":"moe"},{"id":"2306.04640","title":"ModuleFormer: Modularity Emerges from Mixture-of-Experts","created":"2023-06-07","cited_by_count":17,"area":"moe"},{"id":"2409.12136","title":"GRIN: GRadient-INformed MoE","created":"2024-09-18","cited_by_count":17,"area":"moe"},{"id":"2310.04361","title":"Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion","created":"2023-10-06","cited_by_count":16,"area":"moe"},{"id":"2408.08274","title":"BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts","created":"2024-08-15","cited_by_count":16,"area":"moe"},{"id":"2408.11396","title":"MoE-LPR: Multilingual Extension of Large Language Models through Mixture-of-Experts with Language Priors Routing","created":"2024-08-21","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":"2412.05552","title":"SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts","created":"2024-12-07","cited_by_count":16,"area":"moe"},{"id":"2503.05066","title":"Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts","created":"2025-03-07","cited_by_count":15,"area":"moe"},{"id":"2507.11181","title":"Mixture of Experts in Large Language Models","created":"2025-07-15","cited_by_count":15,"area":"moe"},{"id":"2411.18797","title":"SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?","created":"2024-11-27","cited_by_count":14,"area":"moe"},{"id":"2412.20157","title":"UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity","created":"2024-12-28","cited_by_count":14,"area":"moe"},{"id":"2502.10928","title":"Probing Semantic Routing in Large Mixture-of-Expert Models","created":"2025-02-15","cited_by_count":14,"area":"moe"},{"id":"2505.00315","title":"Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing","created":"2025-05-01","cited_by_count":14,"area":"moe"},{"id":"2508.01699","title":"TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding","created":"2025-08-03","cited_by_count":14,"area":"moe"},{"id":"2601.20205","title":"Hyperparameter Transfer with Mixture-of-Expert Layers","created":"2026-01-28","cited_by_count":13,"area":"moe"},{"id":"2410.22884","title":"Stealing User Prompts from Mixture of Experts","created":"2024-10-30","cited_by_count":12,"area":"moe"},{"id":"2402.12399","title":"Turn Waste into Worth: Rectifying Top-$k$ Router of MoE","created":"2024-02-17","cited_by_count":11,"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":"2605.09165","title":"Sparse Layers are Critical to Scaling Looped Language Models","created":"2026-05-09","cited_by_count":11,"area":"moe"},{"id":"2605.18106","title":"Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers","created":"2026-05-18","cited_by_count":11,"area":"moe"},{"id":"2210.07535","title":"AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation","created":"2022-10-14","cited_by_count":10,"area":"moe"},{"id":"2407.11030","title":"DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs","created":"2024-07-03","cited_by_count":10,"area":"moe"},{"id":"2503.01359","title":"DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models","created":"2025-03-03","cited_by_count":10,"area":"moe"},{"id":"2503.23100","title":"MoLAE: Mixture of Latent Experts for Parameter-Efficient Language Models","created":"2025-03-29","cited_by_count":10,"area":"moe"},{"id":"2505.14336","title":"Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach","created":"2025-05-20","cited_by_count":10,"area":"moe"},{"id":"2509.16882","title":"Dynamic Expert Specialization: Towards Catastrophic Forgetting-Free Multi-Domain MoE Adaptation","created":"2025-09-21","cited_by_count":10,"area":"moe"},{"id":"2510.10432","title":"Hierarchical LoRA MoE for Efficient CTR Model Scaling","created":"2025-10-12","cited_by_count":10,"area":"moe"},{"id":"2407.04656","title":"Lazarus: Resilient and Elastic Training of Mixture-of-Experts Models","created":"2024-07-05","cited_by_count":9,"area":"moe"},{"id":"2407.09816","title":"MaskMoE: Boosting Token-Level Learning via Routing Mask in Mixture-of-Experts","created":"2024-07-13","cited_by_count":9,"area":"moe"},{"id":"2410.14574","title":"MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts","created":"2024-10-18","cited_by_count":9,"area":"moe"},{"id":"2411.08212","title":"PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model","created":"2024-11-12","cited_by_count":9,"area":"moe"},{"id":"2212.07571","title":"Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translation","created":"2022-12-15","cited_by_count":8,"area":"moe"},{"id":"2405.15052","title":"Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training","created":"2024-05-23","cited_by_count":8,"area":"moe"},{"id":"2408.12793","title":"La-SoftMoE CLIP for Unified Physical-Digital Face Attack Detection","created":"2024-08-23","cited_by_count":8,"area":"moe"},{"id":"2409.01483","title":"Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning","created":"2024-09-02","cited_by_count":8,"area":"moe"},{"id":"2501.12431","title":"Modality Interactive Mixture-of-Experts for Fake News Detection","created":"2025-01-21","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":"2508.02587","title":"Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules","created":"2025-08-04","cited_by_count":8,"area":"moe"},{"id":"2406.11353","title":"$\\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts","created":"2024-06-17","cited_by_count":7,"area":"moe"},{"id":"2410.10846","title":"Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models","created":"2024-10-01","cited_by_count":7,"area":"moe"},{"id":"2412.16971","title":"Part-Of-Speech Sensitivity of Routers in Mixture of Experts Models","created":"2024-12-22","cited_by_count":7,"area":"moe"},{"id":"2410.12247","title":"EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference","created":"2024-10-16","cited_by_count":6,"area":"moe"},{"id":"2411.00918","title":"LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models","created":"2024-11-01","cited_by_count":6,"area":"moe"},{"id":"2504.01337","title":"Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design","created":"2025-04-02","cited_by_count":6,"area":"moe"},{"id":"2505.07260","title":"UMoE: Unifying Attention and FFN with Shared Experts","created":"2025-05-12","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":"2511.22103","title":"MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding","created":"2025-11-27","cited_by_count":6,"area":"moe"},{"id":"2601.03425","title":"The Illusion of Specialization: Unveiling the Domain-Invariant \"Standing Committee\" in Mixture-of-Experts Models","created":"2026-01-06","cited_by_count":6,"area":"moe"},{"id":"2308.15772","title":"Task-Based MoE for Multitask Multilingual Machine Translation","created":"2023-08-30","cited_by_count":5,"area":"moe"},{"id":"2402.16918","title":"m2mKD: Module-to-Module Knowledge Distillation for Modular Transformers","created":"2024-02-26","cited_by_count":5,"area":"moe"},{"id":"2411.08446","title":"LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing","created":"2024-11-13","cited_by_count":5,"area":"moe"},{"id":"2502.00965","title":"CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling","created":"2025-02-03","cited_by_count":5,"area":"moe"},{"id":"2503.05029","title":"Continual Pre-training of MoEs: How robust is your router?","created":"2025-03-06","cited_by_count":5,"area":"moe"},{"id":"2504.19925","title":"SYMI: Efficient Mixture-of-Experts Training via Model and Optimizer State Decoupling","created":"2025-04-28","cited_by_count":5,"area":"moe"},{"id":"2505.20225","title":"FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models","created":"2025-05-26","cited_by_count":5,"area":"moe"}],"next_cursor":"100"}