{"total":76,"rows":[{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823,"area":"moe"},{"id":"2411.11217","title":"MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs","created":"2024-11-18","cited_by_count":73,"area":"moe"},{"id":"2402.07033","title":"Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models","created":"2024-02-10","cited_by_count":71,"area":"moe"},{"id":"2411.01433","title":"HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference","created":"2024-11-03","cited_by_count":55,"area":"moe"},{"id":"2401.14361","title":"MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache","created":"2024-01-25","cited_by_count":50,"area":"moe"},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47,"area":"moe"},{"id":"2408.10284","title":"AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference","created":"2024-08-19","cited_by_count":42,"area":"moe"},{"id":"2410.22134","title":"ProMoE: Fast MoE-based LLM Serving using Proactive Caching","created":"2024-10-29","cited_by_count":40,"area":"moe"},{"id":"2502.05370","title":"Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading","created":"2025-02-07","cited_by_count":24,"area":"moe"},{"id":"2502.06888","title":"Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline","created":"2025-02-09","cited_by_count":21,"area":"moe"},{"id":"2410.17954","title":"ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling","created":"2024-10-23","cited_by_count":19,"area":"moe"},{"id":"2410.19123","title":"Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design","created":"2024-10-24","cited_by_count":19,"area":"moe"},{"id":"2411.08982","title":"Lynx: Enabling Efficient MoE Inference through Dynamic Batch-Aware Expert Selection","created":"2024-11-13","cited_by_count":16,"area":"moe"},{"id":"2504.05897","title":"HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference","created":"2025-04-08","cited_by_count":16,"area":"moe"},{"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":"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":"2502.12224","title":"Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer Gate","created":"2025-02-17","cited_by_count":13,"area":"moe"},{"id":"2509.25041","title":"GRACE-MoE: Grouping and Replication with Locality-Aware Routing for Efficient Distributed MoE Inference","created":"2025-09-29","cited_by_count":13,"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":"2503.15798","title":"Mixture of Lookup Experts","created":"2025-03-20","cited_by_count":12,"area":"moe"},{"id":"2505.11415","title":"MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems","created":"2025-05-16","cited_by_count":11,"area":"moe"},{"id":"2511.14102","title":"MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts","created":"2025-11-18","cited_by_count":11,"area":"moe"},{"id":"2505.05950","title":"FloE: On-the-Fly MoE Inference on Memory-constrained GPU","created":"2025-05-09","cited_by_count":9,"area":"moe"},{"id":"2509.08342","title":"Accelerating Mixture-of-Expert Inference with Adaptive Expert Split Mechanism","created":"2025-09-10","cited_by_count":9,"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":"2504.02658","title":"MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators","created":"2025-04-03","cited_by_count":8,"area":"moe"},{"id":"2505.16056","title":"Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models","created":"2025-05-21","cited_by_count":8,"area":"moe"},{"id":"2407.14417","title":"Mixture of Experts with Mixture of Precisions for Tuning Quality of Service","created":"2024-07-19","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":"2503.09716","title":"MoE-Gen: High-Throughput MoE Inference on a Single GPU with Module-Based Batching","created":"2025-03-12","cited_by_count":6,"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":"2510.26730","title":"ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference","created":"2025-10-30","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":"2601.21198","title":"ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling","created":"2026-01-29","cited_by_count":4,"area":"moe"},{"id":"2604.10152","title":"SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding","created":"2026-04-11","cited_by_count":4,"area":"moe"},{"id":"2503.00245","title":"CoSMoEs: Compact Sparse Mixture of Experts","created":"2025-02-28","cited_by_count":3,"area":"moe"},{"id":"2504.09345","title":"MoE-Lens: Towards the Hardware Limit of High-Throughput MoE LLM Serving Under Resource Constraints","created":"2025-04-12","cited_by_count":3,"area":"moe"},{"id":"2505.08944","title":"Toward Cost-Efficient Serving of Mixture-of-Experts with Asynchrony","created":"2025-05-13","cited_by_count":3,"area":"moe"},{"id":"2512.17073","title":"Bandwidth-Efficient Adaptive Mixture-of-Experts via Low-Rank Compensation","created":"2025-12-18","cited_by_count":3,"area":"moe"},{"id":"2604.20156","title":"Temporally Extended Mixture-of-Experts Models","created":"2026-04-22","cited_by_count":3,"area":"moe"},{"id":"2608.16157","title":"FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution","created":"2026-08-17","cited_by_count":3,"area":"moe"},{"id":"2511.05814","title":"In-depth Analysis on Caching and Pre-fetching in Mixture of Experts Offloading","created":"2025-11-08","cited_by_count":2,"area":"moe"},{"id":"2602.03495","title":"DALI: A Workload-Aware Offloading Framework for Efficient MoE Inference on Local PCs","created":"2026-02-03","cited_by_count":2,"area":"moe"},{"id":"2602.11192","title":"MELINOE: Fine-Tuning Enables Memory-Efficient Inference for Mixture-of-Experts Models","created":"2026-01-30","cited_by_count":2,"area":"moe"},{"id":"2603.12645","title":"LightMoE: Reducing Mixture-of-Experts Redundancy through Expert Replacing","created":"2026-03-13","cited_by_count":2,"area":"moe"},{"id":"2603.19172","title":"DyMoE: Dynamic Expert Orchestration with Mixed-Precision Quantization for Efficient MoE Inference on Edge","created":"2026-03-19","cited_by_count":2,"area":"moe"},{"id":"2604.23150","title":"Scaling Multi-Node Mixture-of-Experts Inference Using Expert Activation Patterns","created":"2026-04-25","cited_by_count":2,"area":"moe"},{"id":"2605.20179","title":"TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload","created":"2026-05-19","cited_by_count":2,"area":"moe"},{"id":"2606.21868","title":"WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware","created":"2026-06-20","cited_by_count":2,"area":"moe"},{"id":"2508.19078","title":"Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devices","created":"2025-08-26","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":"2512.16473","title":"Efficient CPU-GPU Collaborative Inference for MoE-based LLMs on Memory-Limited Systems","created":"2025-12-18","cited_by_count":1,"area":"moe"},{"id":"2512.21487","title":"Efficient MoE Inference with Fine-Grained Scheduling of Disaggregated Expert Parallelism","created":"2025-12-25","cited_by_count":1,"area":"moe"},{"id":"2601.17063","title":"FlashMoE: Reducing SSD I/O Bottlenecks via ML-Based Cache Replacement for Mixture-of-Experts Inference on Edge Devices","created":"2026-01-22","cited_by_count":1,"area":"moe"},{"id":"2603.06350","title":"MoEless: Efficient MoE LLM Serving via Serverless Computing","created":"2026-03-06","cited_by_count":1,"area":"moe"},{"id":"2603.19289","title":"Speculating Experts Accelerates Inference for Mixture-of-Experts","created":"2026-03-09","cited_by_count":1,"area":"moe"},{"id":"2605.21427","title":"PALS: Power-Aware LLM Serving for Mixture-of-Experts Models","created":"2026-05-20","cited_by_count":1,"area":"moe"},{"id":"2606.21428","title":"Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study","created":"2026-06-19","cited_by_count":1,"area":"moe"},{"id":"2606.29982","title":"Beyond Uniform Experts: Cost-Aware Expert Execution for Efficient Multi-Device MoE Inference","created":"2026-06-29","cited_by_count":1,"area":"moe"},{"id":"2505.06481","title":"QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration","created":"2025-05-10","cited_by_count":0,"area":"moe"},{"id":"2509.02408","title":"Cache Management for Mixture-of-Experts LLMs -- extended version","created":"2025-09-02","cited_by_count":0,"area":"moe"},{"id":"2601.03992","title":"A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems","created":"2026-01-07","cited_by_count":0,"area":"moe"},{"id":"2603.01058","title":"TriMoE: Augmenting GPU with AMX-Enabled CPU and DIMM-NDP for High-Throughput MoE Inference via Offloading","created":"2026-03-01","cited_by_count":0,"area":"moe"},{"id":"2603.27624","title":"Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling","created":"2026-03-29","cited_by_count":0,"area":"moe"},{"id":"2605.05899","title":"VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading","created":"2026-05-07","cited_by_count":0,"area":"moe"},{"id":"2608.07814","title":"Shape Mutating Expert Compression:LorExperts and BTExperts","created":"2026-08-07","cited_by_count":0,"area":"moe"},{"id":"2608.07911","title":"Reproducible Evaluation of MoE Expert Caching: Replay Semantics, Workload Contamination, and Operating Regimes","created":"2026-08-08","cited_by_count":0,"area":"moe"},{"id":"2608.11688","title":"APEX: Adaptive Expert Prefetching for Memory-Efficient Edge MoE Inference","created":"2026-08-12","cited_by_count":0,"area":"moe"},{"id":"2608.21693","title":"Benchmarking Composable Compression Techniques in Mixture-of-Experts LLMs","created":"2026-08-22","cited_by_count":0,"area":"moe"},{"id":"2609.06551","title":"EStream: Fast and Memory-Efficient MoE Prefill through Expert Virtualization on Mobile NPUs","created":"2026-09-06","cited_by_count":0,"area":"moe"},{"id":"2609.18063","title":"The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction","created":"2026-09-16","cited_by_count":0,"area":"moe"},{"id":"2609.18842","title":"Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data","created":"2026-09-16","cited_by_count":0,"area":"moe"},{"id":"2609.34077","title":"MaskCoFT: Masked Co-Adaptive Fine-Tuning for Memory-Efficient MoE Inference","created":"2026-09-28","cited_by_count":0,"area":"moe"},{"id":"2609.38090","title":"Mira: Memory-Efficient MoE Inference Using Adaptive Caching and Predictive Expert Staging","created":"2026-09-29","cited_by_count":0,"area":"moe"},{"id":"2610.09424","title":"Democratizing MoE inference on commodity GPUs with CoMoE","created":"2026-10-07","cited_by_count":0,"area":"moe"},{"id":"2610.15417","title":"SpecFit: Not All Draft Tokens Cost the Same in Offloaded MoE Inference","created":"2026-10-11","cited_by_count":0,"area":"moe"}],"next_cursor":null}