{"total":180,"rows":[{"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":"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":"2411.11217","title":"MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs","created":"2024-11-18","cited_by_count":73,"area":"moe"},{"id":"2510.11370","title":"Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers","created":"2025-10-13","cited_by_count":72,"area":"moe"},{"id":"2507.19427","title":"Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding","created":"2025-07-25","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":"2410.22134","title":"ProMoE: Fast MoE-based LLM Serving using Proactive Caching","created":"2024-10-29","cited_by_count":40,"area":"moe"},{"id":"2406.05955","title":"Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters","created":"2024-06-10","cited_by_count":38,"area":"moe"},{"id":"2603.03276","title":"Beyond Language Modeling: An Exploration of Multimodal Pretraining","created":"2026-03-03","cited_by_count":37,"area":"moe"},{"id":"2409.01141","title":"Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching","created":"2024-09-02","cited_by_count":34,"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":"2505.05799","title":"MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design","created":"2025-05-09","cited_by_count":30,"area":"moe"},{"id":"2510.04694","title":"Multilingual Routing in Mixture-of-Experts","created":"2025-10-06","cited_by_count":29,"area":"moe"},{"id":"2509.10377","title":"Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs","created":"2025-09-12","cited_by_count":25,"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":"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":"2504.15299","title":"D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving","created":"2025-04-17","cited_by_count":20,"area":"moe"},{"id":"2404.02852","title":"Toward Inference-optimal Mixture-of-Expert Large Language Models","created":"2024-04-03","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":"2505.19645","title":"MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE","created":"2025-05-26","cited_by_count":19,"area":"moe"},{"id":"2405.17741","title":"LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-design","created":"2024-05-28","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":"2502.10928","title":"Probing Semantic Routing in Large Mixture-of-Expert Models","created":"2025-02-15","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":"2506.20675","title":"Utility-Driven Speculative Decoding for Mixture-of-Experts","created":"2025-06-17","cited_by_count":13,"area":"moe"},{"id":"2508.15036","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","created":"2025-08-20","cited_by_count":13,"area":"moe"},{"id":"2509.17863","title":"Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving","created":"2025-09-22","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":"2506.07533","title":"MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts","created":"2025-06-09","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":"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":"2602.10693","title":"VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training","created":"2026-02-11","cited_by_count":11,"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":"2604.04356","title":"REAM: Merging Improves Pruning of Experts in LLMs","created":"2026-04-06","cited_by_count":10,"area":"moe"},{"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":"2505.03531","title":"Faster MoE LLM Inference for Extremely Large Models","created":"2025-05-06","cited_by_count":9,"area":"moe"},{"id":"2604.08541","title":"Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts","created":"2026-04-09","cited_by_count":9,"area":"moe"},{"id":"2606.04101","title":"UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing","created":"2026-06-02","cited_by_count":9,"area":"moe"},{"id":"2508.21706","title":"Accelerating Mixture-of-Experts Inference by Hiding Offloading Latency with Speculative Decoding","created":"2025-08-29","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":"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":"2506.12417","title":"HarMoEny: Efficient Multi-GPU Inference of MoE Models","created":"2025-06-14","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":"2602.07265","title":"XShare: Collaborative in-Batch Expert Sharing for Faster MoE Inference","created":"2026-02-06","cited_by_count":7,"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":"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":"2509.02753","title":"LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference","created":"2025-09-02","cited_by_count":6,"area":"moe"},{"id":"2603.17102","title":"Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency","created":"2026-03-17","cited_by_count":6,"area":"moe"},{"id":"2506.05767","title":"dots.llm1 Technical Report","created":"2025-06-06","cited_by_count":5,"area":"moe"},{"id":"2509.02512","title":"MoPEQ: Mixture of Mixed Precision Quantized Experts","created":"2025-09-02","cited_by_count":5,"area":"moe"},{"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":"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":"2603.13606","title":"NCCL EP: Towards a Unified Expert Parallel Communication API for NCCL","created":"2026-03-13","cited_by_count":5,"area":"moe"},{"id":"2604.19241","title":"UniEP: Unified Expert-Parallel MoE MegaKernel for LLM Training","created":"2026-04-21","cited_by_count":5,"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":"2507.18671","title":"Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling","created":"2025-07-24","cited_by_count":4,"area":"moe"},{"id":"2510.02613","title":"ElasticMoE: An Efficient Auto Scaling Method for Mixture-of-Experts Models","created":"2025-10-02","cited_by_count":4,"area":"moe"},{"id":"2510.08055","title":"From Tokens to Layers: Redefining Stall-Free Scheduling for MoE Serving with Layered Prefill","created":"2025-10-09","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":"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":"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":"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":"2508.13337","title":"X-MoE: Enabling Scalable Training for Emerging Mixture-of-Experts Architectures on HPC Platforms","created":"2025-08-18","cited_by_count":3,"area":"moe"},{"id":"2508.19373","title":"HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference","created":"2025-08-26","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":"2605.27081","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","created":"2026-05-26","cited_by_count":3,"area":"moe"},{"id":"2605.28042","title":"Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts","created":"2026-05-27","cited_by_count":3,"area":"moe"},{"id":"2606.04300","title":"Argus-Retriever: Vision-LLM Late-Interaction Retrieval with Region-Aware Query-Conditioned MoE for Visual Document Retrieval","created":"2026-06-03","cited_by_count":3,"area":"moe"},{"id":"2607.00466","title":"ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving","created":"2026-07-01","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":"2609.04895","title":"Cache-Aware Joint Router Adaptation for Memory-Efficient MoE Inference","created":"2026-09-04","cited_by_count":3,"area":"moe"},{"id":"2411.08968","title":"Sparse Upcycling: Inference Inefficient Finetuning","created":"2024-11-13","cited_by_count":2,"area":"moe"},{"id":"2504.15527","title":"Compass-V2 Technical Report","created":"2025-04-22","cited_by_count":2,"area":"moe"},{"id":"2505.21191","title":"Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities","created":"2025-05-27","cited_by_count":2,"area":"moe"},{"id":"2508.03148","title":"Frontier: Simulating the Next Generation of LLM Inference Systems","created":"2025-08-05","cited_by_count":2,"area":"moe"},{"id":"2508.16700","title":"GPT-OSS-20B: A Comprehensive Deployment-Centric Analysis of OpenAI's Open-Weight Mixture of Experts Model","created":"2025-08-22","cited_by_count":2,"area":"moe"},{"id":"2509.06346","title":"Ban&Pick: Enhancing Performance and Efficiency of MoE-LLMs via Smarter Routing","created":"2025-09-08","cited_by_count":2,"area":"moe"},{"id":"2512.23995","title":"RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stress","created":"2025-12-30","cited_by_count":2,"area":"moe"},{"id":"2601.07022","title":"Solar Open Technical Report","created":"2026-01-11","cited_by_count":2,"area":"moe"},{"id":"2602.08019","title":"The Rise of Sparse Mixture-of-Experts: A Survey from Algorithmic Foundations to Decentralized Architectures and Vertical Domain Applications","created":"2026-02-08","cited_by_count":2,"area":"moe"},{"id":"2603.11873","title":"AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization","created":"2026-03-12","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":"2605.10670","title":"Surviving Partial Rank Failures in Wide Expert-Parallel MoE Inference","created":"2026-05-11","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":"2605.28302","title":"How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving","created":"2026-05-27","cited_by_count":2,"area":"moe"},{"id":"2606.05538","title":"Less is MoE: Trimming Experts in Domain-Specialist Language Models","created":"2026-06-04","cited_by_count":2,"area":"moe"},{"id":"2606.11867","title":"Harnessing Routing Foresight for Micro-step-level MoE load balancing in RL Post-training","created":"2026-06-10","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":"2607.16184","title":"PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization","created":"2026-07-17","cited_by_count":2,"area":"moe"},{"id":"2608.24938","title":"ExFold: Unified Expert Folding for Training-Free MoE Prefill-Decode Acceleration","created":"2026-08-24","cited_by_count":2,"area":"moe"},{"id":"2608.28044","title":"Characterization of Request and Token Energy Costs for LLM Inference Workloads on GPU Platforms","created":"2026-08-28","cited_by_count":2,"area":"moe"},{"id":"2510.19366","title":"MoE-Prism: Disentangling Monolithic Experts for Elastic MoE Services via Model-System Co-Designs","created":"2025-10-22","cited_by_count":1,"area":"moe"},{"id":"2511.11505","title":"FarSkip-Collective: Unhobbling Blocking Communication in Mixture of Experts Models","created":"2025-11-14","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"}],"next_cursor":"100"}