{"total":104,"rows":[{"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":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"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":"2505.22323","title":"Advancing Expert Specialization for Better MoE","created":"2025-05-28","cited_by_count":39,"area":"moe"},{"id":"2502.17298","title":"Delta Decompression for MoE-based LLMs Compression","created":"2025-02-24","cited_by_count":33,"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":"2504.02263","title":"MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism","created":"2025-04-03","cited_by_count":32,"area":"moe"},{"id":"2502.06643","title":"MoETuner: Optimized Mixture of Expert Serving with Balanced Expert Placement and Token Routing","created":"2025-02-10","cited_by_count":26,"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":"2501.16352","title":"Mixture of Experts (MoE): A Big Data Perspective","created":"2025-01-18","cited_by_count":18,"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":"2510.18586","title":"TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications","created":"2025-10-21","cited_by_count":16,"area":"inference"},{"id":"2507.11181","title":"Mixture of Experts in Large Language Models","created":"2025-07-15","cited_by_count":15,"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":"2506.20675","title":"Utility-Driven Speculative Decoding for Mixture-of-Experts","created":"2025-06-17","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":"2503.06823","title":"eMoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference","created":"2025-03-10","cited_by_count":11,"area":"moe"},{"id":"2411.17741","title":"Chameleon: Adaptive Caching and Scheduling for Many-Adapter LLM Inference Environments","created":"2024-11-24","cited_by_count":9,"area":"inference"},{"id":"2503.04398","title":"Semantic Parallelism: Redefining Efficient MoE Inference via Model-Data Co-Scheduling","created":"2025-03-06","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":"2602.23036","title":"LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure","created":"2026-02-26","cited_by_count":9,"area":"inference"},{"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":"2509.23638","title":"LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers","created":"2025-09-28","cited_by_count":8,"area":"moe"},{"id":"2512.13525","title":"Janus: Disaggregating Attention and Experts for Scalable MoE Inference","created":"2025-12-15","cited_by_count":8,"area":"moe"},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2410.17043","title":"Optimizing Mixture-of-Experts Inference Time Combining Model Deployment and Communication Scheduling","created":"2024-10-22","cited_by_count":7,"area":"moe"},{"id":"2412.20185","title":"DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization","created":"2024-12-28","cited_by_count":7,"area":null},{"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":"2511.02237","title":"Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining","created":"2025-11-04","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":"2602.09316","title":"Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density","created":"2026-02-10","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":"2511.07229","title":"LLMServingSim2.0: A Unified Simulator for Heterogeneous Hardware and Serving Techniques in LLM Infrastructure","created":"2025-11-10","cited_by_count":6,"area":null},{"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":"2503.02354","title":"CoServe: Efficient Collaboration-of-Experts (CoE) Model Inference with Limited Memory","created":"2025-03-04","cited_by_count":5,"area":null},{"id":"2509.07379","title":"DuoServe-MoE: Dual-Phase Expert Prefetch and Caching for LLM Inference QoS Assurance","created":"2025-09-09","cited_by_count":5,"area":"moe"},{"id":"2510.03293","title":"From Score Distributions to Balance: Plug-and-Play Mixture-of-Experts Routing","created":"2025-09-29","cited_by_count":5,"area":"moe"},{"id":"2511.10054","title":"BuddyMoE: Exploiting Expert Redundancy to Accelerate Memory-Constrained Mixture-of-Experts Inference","created":"2025-11-13","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":"2408.04307","title":"MoC-System: Efficient Fault Tolerance for Sparse Mixture-of-Experts Model Training","created":"2024-08-08","cited_by_count":4,"area":"moe"},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2502.05602","title":"UbiMoE: A Ubiquitous Mixture-of-Experts Vision Transformer Accelerator With Hybrid Computation Pattern on FPGA","created":"2025-02-08","cited_by_count":4,"area":"moe"},{"id":"2505.13345","title":"Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference","created":"2025-05-19","cited_by_count":4,"area":"moe"},{"id":"2507.17133","title":"BrownoutServe: SLO-Aware Inference Serving under Bursty Workloads for MoE-based LLMs","created":"2025-07-23","cited_by_count":4,"area":"moe"},{"id":"2508.06978","title":"SSD Offloading for LLM Mixture-of-Experts Weights Considered Harmful in Energy Efficiency","created":"2025-08-09","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":"2505.08944","title":"Toward Cost-Efficient Serving of Mixture-of-Experts with Asynchrony","created":"2025-05-13","cited_by_count":3,"area":"moe"},{"id":"2512.12990","title":"SliceMoE: Bit-Sliced Expert Caching under Miss-Rate Constraints for Efficient MoE Inference","created":"2025-12-15","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":"2601.03577","title":"Variational Inference, Entropy, and Orthogonality: A Unified Theory of Mixture-of-Experts","created":"2026-01-07","cited_by_count":3,"area":"moe"},{"id":"2606.15453","title":"A Spatio-Temporal Expert Prefetching Framework for Efficient MoE-based LLM Inference","created":"2026-06-13","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":"2508.09208","title":"CoMoE: Collaborative Optimization of Expert Aggregation and Offloading for MoE-based LLMs at Edge","created":"2025-08-10","cited_by_count":2,"area":"moe"},{"id":"2512.04476","title":"Context-Aware Mixture-of-Experts Inference on CXL-Enabled GPU-NDP Systems","created":"2025-12-04","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":"2605.02960","title":"MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving","created":"2026-05-03","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":"2607.08780","title":"Sticky Routing: Training MoE Models for Memory-Efficient Inference","created":"2026-06-12","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":"2510.12357","title":"MoBiLE: Efficient Mixture-of-Experts Inference on Consumer GPU with Mixture of Big Little Experts","created":"2025-10-14","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":"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":"2603.19289","title":"Speculating Experts Accelerates Inference for Mixture-of-Experts","created":"2026-03-09","cited_by_count":1,"area":"moe"},{"id":"2604.07609","title":"Blink: CPU-Free LLM Inference by Delegating the Serving Stack to GPU and SmartNIC","created":"2026-04-08","cited_by_count":1,"area":null},{"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":"2503.01268","title":"Multi-Level Collaboration in Model Merging","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2505.23184","title":"Two Is Better Than One: Rotations Scale LoRAs","created":"2025-05-29","cited_by_count":0,"area":"moe"},{"id":"2602.19938","title":"A Replicate-and-Quantize Strategy for Plug-and-Play Load Balancing of Sparse Mixture-of-Experts LLMs","created":"2026-02-23","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":"2604.02715","title":"FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving","created":"2026-04-03","cited_by_count":0,"area":"moe"},{"id":"2604.03342","title":"Mixture-of-Experts in Remote Sensing: A Survey","created":"2026-04-03","cited_by_count":0,"area":"moe"},{"id":"2604.14626","title":"ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving","created":"2026-04-16","cited_by_count":0,"area":"moe"},{"id":"2605.05888","title":"MoE-Hub: Taming Software Complexity for Seamless MoE Overlap with Hardware-Accelerated Communication on Multi-GPU Systems","created":"2026-05-07","cited_by_count":0,"area":"moe"},{"id":"2605.11537","title":"Fast MoE Inference via Predictive Prefetching and Expert Replication","created":"2026-05-12","cited_by_count":0,"area":"moe"},{"id":"2605.17889","title":"CoX-MoE: Coalesced Expert Execution for High-Throughput MoE Inference with AMX-Enabled CPU-GPU Co-Execution","created":"2026-05-18","cited_by_count":0,"area":"moe"},{"id":"2605.23294","title":"NASiC: 3D NAND-based CAM-Selected Multibit CIM Architecture for Efficient On-Device Mixture-of-Experts LLM Inference","created":"2026-05-22","cited_by_count":0,"area":"moe"},{"id":"2608.05303","title":"EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding","created":"2026-08-05","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":"2608.13962","title":"MoE Expert Execution in Disaggregated LLM Serving with a High-Bandwidth ReRAM Near-Memory Architecture","created":"2026-08-14","cited_by_count":0,"area":"moe"},{"id":"2608.26650","title":"Meta-Learning Where to Allocate Experts: Task-Conditioned Layer-Wise Compression for MoEs","created":"2026-08-27","cited_by_count":0,"area":"moe"},{"id":"2609.00407","title":"DynaNDE: Dynamic Near-Data Expert Scheduling for Batched MoE Inference","created":"2026-08-31","cited_by_count":0,"area":"moe"},{"id":"2609.04238","title":"Budgeting Bytes: A Windowed Storage Roofline and Dual-Budget Architecture Ablations for Storage-Bound LLM Decoding","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.12978","title":"SeqMoE: Toward Full-Load Performance via Predictive and Graph-Compatible MoE Offloading","created":"2026-09-11","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":"2609.21137","title":"A Multi-Engine Dataflow for MoE Decoding on Scratchpad-Based Tensor Accelerators","created":"2026-09-17","cited_by_count":0,"area":"moe"},{"id":"2609.26061","title":"TopoCompress: Topology Aware Token Compression Algorithm for Distributed Edge MoE Inference","created":"2026-08-01","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":"2609.36222","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"}],"next_cursor":"100"}