{"total":173,"rows":[{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"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":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2407.04153","title":"Mixture of A Million Experts","created":"2024-07-04","cited_by_count":72,"area":"moe"},{"id":"2405.01029","title":"MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts","created":"2024-05-02","cited_by_count":70,"area":"moe"},{"id":"2405.16039","title":"MoEUT: Mixture-of-Experts Universal Transformers","created":"2024-05-25","cited_by_count":59,"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":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"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":"2504.07951","title":"Scaling Laws for Native Multimodal Models","created":"2025-04-10","cited_by_count":50,"area":null},{"id":"2410.07524","title":"Upcycling Large Language Models into Mixture of Experts","created":"2024-10-10","cited_by_count":49,"area":"moe"},{"id":"2410.08527","title":"Scaling Laws for Predicting Downstream Performance in LLMs","created":"2024-10-11","cited_by_count":48,"area":null},{"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":"2505.13738","title":"Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training","created":"2025-05-19","cited_by_count":43,"area":null},{"id":"2409.19913","title":"Scaling Optimal LR Across Token Horizons","created":"2024-09-30","cited_by_count":40,"area":null},{"id":"2503.09146","title":"Generative Frame Sampler for Long Video Understanding","created":"2025-03-12","cited_by_count":37,"area":null},{"id":"2502.07972","title":"Training Sparse Mixture Of Experts Text Embedding Models","created":"2025-02-11","cited_by_count":32,"area":"moe"},{"id":"2502.10940","title":"CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation","created":"2025-02-16","cited_by_count":28,"area":null},{"id":"2408.11304","title":"FedMoE: Personalized Federated Learning via Heterogeneous Mixture of Experts","created":"2024-08-21","cited_by_count":27,"area":"moe"},{"id":"2410.11840","title":"A Hitchhiker's Guide to Scaling Law Estimation","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2410.12883","title":"Scaling Laws for Multilingual Language Models","created":"2024-10-15","cited_by_count":23,"area":null},{"id":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2411.02335","title":"Sparsing Law: Towards Large Language Models with Greater Activation Sparsity","created":"2024-11-04","cited_by_count":22,"area":null},{"id":"2412.01505","title":"Scaling Law for Language Models Training Considering Batch Size","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"area":null},{"id":"2410.19034","title":"Mixture of Parrots: Experts improve memorization more than reasoning","created":"2024-10-24","cited_by_count":21,"area":"moe"},{"id":"2512.14080","title":"SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations","created":"2025-12-16","cited_by_count":21,"area":"moe"},{"id":"2502.06857","title":"Gemstones: A Model Suite for Multi-Faceted Scaling Laws","created":"2025-02-07","cited_by_count":20,"area":null},{"id":"2411.12364","title":"Ultra-Sparse Memory Network","created":"2024-11-19","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":"2507.00029","title":"LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing","created":"2025-06-17","cited_by_count":18,"area":"moe"},{"id":"2508.01625","title":"EAC-MoE: Expert-Selection Aware Compressor for Mixture-of-Experts Large Language Models","created":"2025-08-03","cited_by_count":18,"area":"moe"},{"id":"2609.01343","title":"SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers","created":"2026-09-01","cited_by_count":18,"area":"moe"},{"id":"2504.14960","title":"MoE Parallel Folding: Heterogeneous Parallelism Mappings for Efficient Large-Scale MoE Model Training with Megatron Core","created":"2025-04-21","cited_by_count":17,"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":"2501.18107","title":"Scaling Inference-Efficient Language Models","created":"2025-01-30","cited_by_count":16,"area":null},{"id":"2403.08245","title":"Scattered Mixture-of-Experts Implementation","created":"2024-03-13","cited_by_count":15,"area":"moe"},{"id":"2407.02118","title":"Breaking Language Barriers: Cross-Lingual Continual Pre-Training at Scale","created":"2024-07-02","cited_by_count":15,"area":null},{"id":"2409.06669","title":"DA-MoE: Towards Dynamic Expert Allocation for Mixture-of-Experts Models","created":"2024-09-10","cited_by_count":15,"area":"moe"},{"id":"2502.04327","title":"Value-Based Deep RL Scales Predictably","created":"2025-02-06","cited_by_count":15,"area":"deeprl"},{"id":"2412.00099","title":"Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference","created":"2024-11-27","cited_by_count":14,"area":"moe"},{"id":"2412.04139","title":"Monet: Mixture of Monosemantic Experts for Transformers","created":"2024-12-05","cited_by_count":13,"area":"mechinterp"},{"id":"2502.03009","title":"Scaling Laws for Upcycling Mixture-of-Experts Language Models","created":"2025-02-05","cited_by_count":13,"area":"moe"},{"id":"2507.21184","title":"Can Language Models Discover Scaling Laws?","created":"2025-07-27","cited_by_count":13,"area":null},{"id":"2601.20205","title":"Hyperparameter Transfer with Mixture-of-Expert Layers","created":"2026-01-28","cited_by_count":13,"area":"moe"},{"id":"2605.01640","title":"Prescriptive Scaling Laws for Data Constrained Training","created":"2026-05-02","cited_by_count":12,"area":null},{"id":"2411.16035","title":"Predicting Emergent Capabilities by Finetuning","created":"2024-11-25","cited_by_count":10,"area":null},{"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":"2509.23678","title":"Towards a Comprehensive Scaling Law of Mixture-of-Experts","created":"2025-09-28","cited_by_count":10,"area":"moe"},{"id":"2510.05245","title":"Stratum: System-Hardware Co-Design with Tiered Monolithic 3D-Stackable DRAM for Efficient MoE Serving","created":"2025-10-06","cited_by_count":10,"area":"moe"},{"id":"2510.17483","title":"ReXMoE: Reusing Experts with Minimal Overhead in Mixture-of-Experts","created":"2025-10-20","cited_by_count":10,"area":"moe"},{"id":"2406.08155","title":"QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts","created":"2024-06-12","cited_by_count":9,"area":"moe"},{"id":"2505.06839","title":"The power of fine-grained experts: Granularity boosts expressivity in Mixture of Experts","created":"2025-05-11","cited_by_count":9,"area":"moe"},{"id":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2603.04971","title":"Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation","created":"2026-03-05","cited_by_count":8,"area":"moe"},{"id":"2510.05781","title":"Mixture of Neuron Experts","created":"2025-10-07","cited_by_count":7,"area":"moe"},{"id":"2408.09895","title":"Performance Law of Large Language Models","created":"2024-08-19","cited_by_count":6,"area":null},{"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":"2505.07260","title":"UMoE: Unifying Attention and FFN with Shared Experts","created":"2025-05-12","cited_by_count":6,"area":"moe"},{"id":"2507.08771","title":"BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity","created":"2025-07-11","cited_by_count":6,"area":"moe"},{"id":"2508.14881","title":"Compute-Optimal Scaling for Value-Based Deep RL","created":"2025-08-20","cited_by_count":6,"area":"deeprl"},{"id":"2511.06494","title":"Route Experts by Sequence, not by Token","created":"2025-11-09","cited_by_count":6,"area":"moe"},{"id":"2605.12715","title":"Scaling Laws for Mixture Pretraining Under Data Constraints","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2502.12051","title":"How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines","created":"2025-02-17","cited_by_count":5,"area":null},{"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":"2505.00985","title":"Position: Enough of Scaling LLMs! Lets Focus on Downscaling","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2506.21035","title":"Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts","created":"2025-06-26","cited_by_count":5,"area":"moe"},{"id":"2507.00004","title":"A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search","created":"2025-06-10","cited_by_count":5,"area":"lr"},{"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":"2602.10377","title":"Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs","created":"2026-02-10","cited_by_count":5,"area":"vla"},{"id":"2603.06626","title":"Grouter: Decoupling Routing from Representation for Accelerated MoE Training","created":"2026-02-22","cited_by_count":5,"area":"moe"},{"id":"2408.04278","title":"LaDiMo: Layer-wise Distillation Inspired MoEfier","created":"2024-08-08","cited_by_count":4,"area":"moe"},{"id":"2510.04136","title":"MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition","created":"2025-10-05","cited_by_count":4,"area":"moe"},{"id":"2510.18245","title":"Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2602.09721","title":"Revealing the Challenges of Attention-FFN Disaggregation for Modern MoE Models and Hardware Systems","created":"2026-02-10","cited_by_count":4,"area":"moe"},{"id":"2605.01188","title":"Compute Optimal Tokenization","created":"2026-05-02","cited_by_count":4,"area":null},{"id":"2606.17952","title":"SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs","created":"2026-06-16","cited_by_count":4,"area":"moe"},{"id":"2411.01137","title":"Data movement limits to frontier model training","created":"2024-11-02","cited_by_count":3,"area":null},{"id":"2412.15411","title":"Sparse Checkpointing for Fast and Reliable MoE Training","created":"2024-12-19","cited_by_count":3,"area":"moe"},{"id":"2502.01804","title":"Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2504.06426","title":"S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning","created":"2025-04-08","cited_by_count":3,"area":"moe"},{"id":"2508.09752","title":"$\\mu$-Parametrization for Mixture of Experts","created":"2025-08-13","cited_by_count":3,"area":"moe"},{"id":"2510.00570","title":"Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning","created":"2025-10-01","cited_by_count":3,"area":"moe"},{"id":"2512.13996","title":"DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training","created":"2025-12-16","cited_by_count":3,"area":"moe"},{"id":"2512.23407","title":"Theoretical Foundations of Scaling Law in Familial Models","created":"2025-12-29","cited_by_count":3,"area":null},{"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":"2603.11535","title":"Expert Threshold Routing for Autoregressive Language Modeling with Dynamic Computation Allocation and Load Balancing","created":"2026-03-12","cited_by_count":3,"area":"moe"},{"id":"2604.22753","title":"Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection","created":"2026-04-24","cited_by_count":3,"area":null},{"id":"2605.27358","title":"MobileMoE: Scaling On-Device Mixture of Experts","created":"2026-05-26","cited_by_count":3,"area":"moe"},{"id":"2503.11905","title":"Upcycling Text-to-Image Diffusion Models for Multi-Task Capabilities","created":"2025-03-14","cited_by_count":2,"area":"diffusion"},{"id":"2506.02890","title":"Scaling Fine-Grained MoE Beyond 50B Parameters: Empirical Evaluation and Practical Insights","created":"2025-06-03","cited_by_count":2,"area":"moe"},{"id":"2507.03526","title":"Decoupled Relative Learning Rate Schedules","created":"2025-07-04","cited_by_count":2,"area":"moe"},{"id":"2507.19142","title":"A3D-MoE: Acceleration of Large Language Models with Mixture of Experts via 3D Heterogeneous Integration","created":"2025-07-25","cited_by_count":2,"area":"moe"},{"id":"2510.01185","title":"Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs","created":"2025-10-01","cited_by_count":2,"area":"moe"},{"id":"2510.02721","title":"Hyperparameter Loss Surfaces Are Simple Near their Optima","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2512.18452","title":"Secret mixtures of experts inside your LLM","created":"2025-12-20","cited_by_count":2,"area":"moe"},{"id":"2601.21461","title":"L$^3$: Large Lookup Layers","created":"2026-01-29","cited_by_count":2,"area":"moe"},{"id":"2602.10300","title":"Configuration-to-Performance Scaling Law with Neural Ansatz","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2602.17798","title":"Grassmannian Mixture-of-Experts: Concentration-Controlled Routing on Subspace Manifolds","created":"2026-02-19","cited_by_count":2,"area":"moe"}],"next_cursor":"100"}