{"total":31,"rows":[{"id":"2312.17238","title":"Fast Inference of Mixture-of-Experts Language Models with Offloading","created":"2023-12-28","cited_by_count":91,"area":"moe"},{"id":"2410.12013","title":"MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router","created":"2024-10-15","cited_by_count":62,"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":"2310.16795","title":"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models","created":"2023-10-25","cited_by_count":42,"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":"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":"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":"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":"2602.16052","title":"MoE-Spec: Expert Budgeting for Efficient Speculative Decoding","created":"2026-02-17","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":"2506.13329","title":"EAQuant: Enhancing Post-Training Quantization for MoE Models via Expert-Aware Optimization","created":"2025-06-16","cited_by_count":10,"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":"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":"2605.23078","title":"GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs","created":"2026-05-21","cited_by_count":7,"area":"moe"},{"id":"2503.21135","title":"DynaMo: Runtime Switchable Quantization for MoE with Cross-Dataset Adaptation","created":"2025-03-27","cited_by_count":4,"area":"moe"},{"id":"2604.06515","title":"Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees","created":"2026-04-07","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":"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":"2605.09281","title":"TileQ: Efficient Low-Rank Quantization of Mixture-of-Experts with 2D Tiling","created":"2026-05-10","cited_by_count":1,"area":"moe"},{"id":"2506.18349","title":"SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and Distillation","created":"2025-06-23","cited_by_count":0,"area":"moe"},{"id":"2601.13563","title":"ButterflyMoE: Compression-Scalable Ternary Experts via Structured Butterfly Orbits","created":"2026-01-20","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":"2607.20981","title":"Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligence","created":"2026-07-23","cited_by_count":0,"area":"moe"},{"id":"2607.28097","title":"From Expert Reduction to Behavioral Divergence: Tracing Numerical State through Sparse MoE Inference","created":"2026-07-30","cited_by_count":0,"area":"moe"},{"id":"2608.08910","title":"Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving","created":"2026-08-09","cited_by_count":0,"area":"moe"},{"id":"2608.15383","title":"Every Expert Counts: ExactMoE for Memory-Efficient W4A16 Inference","created":"2026-08-15","cited_by_count":0,"area":"moe"},{"id":"2609.12550","title":"Quality-Constrained Routing over a Fixed Pool of Quantized Mixture-of-Experts Instances","created":"2026-09-11","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"}],"next_cursor":null}