{"total":30,"rows":[{"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":"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":"2506.23266","title":"Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging","created":"2025-06-29","cited_by_count":28,"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":"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":"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":"2507.23279","title":"Unveiling Super Experts in Mixture-of-Experts Large Language Models","created":"2025-07-31","cited_by_count":17,"area":"moe"},{"id":"2507.00390","title":"MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoE","created":"2025-07-01","cited_by_count":13,"area":"moe"},{"id":"2603.06003","title":"EvoESAP: Non-Uniform Expert Pruning for Sparse MoE","created":"2026-03-06","cited_by_count":9,"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":"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":"2605.23078","title":"GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs","created":"2026-05-21","cited_by_count":7,"area":"moe"},{"id":"2606.04980","title":"AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization","created":"2026-06-03","cited_by_count":7,"area":"moe"},{"id":"2509.02512","title":"MoPEQ: Mixture of Mixed Precision Quantized Experts","created":"2025-09-02","cited_by_count":5,"area":"moe"},{"id":"2602.00879","title":"Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs","created":"2026-01-31","cited_by_count":4,"area":"moe"},{"id":"2509.22299","title":"HEAPr: Hessian-based Efficient Atomic Expert Pruning in Output Space","created":"2025-09-26","cited_by_count":3,"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":"2603.12645","title":"LightMoE: Reducing Mixture-of-Experts Redundancy through Expert Replacing","created":"2026-03-13","cited_by_count":2,"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":"2604.10603","title":"MoEITS: A Green AI approach for simplifying MoE-LLMs","created":"2026-04-12","cited_by_count":1,"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":"2603.02633","title":"Robust Heterogeneous Analog-Digital Computing for Mixture-of-Experts Models with Theoretical Generalization Guarantees","created":"2026-03-03","cited_by_count":0,"area":"moe"},{"id":"2605.16349","title":"Geometric Asymmetry in MoE Specialization: Functional Decorrelation and Representational Overlap","created":"2026-05-08","cited_by_count":0,"area":"moe"},{"id":"2606.18304","title":"Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression","created":"2026-06-16","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":"2609.38823","title":"DecoMoE: Decoupling Visual Propagation and Expert Computation for Efficient Multimodal MoE Inference","created":"2026-09-30","cited_by_count":0,"area":"moe"},{"id":"2610.02241","title":"Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts","created":"2026-09-29","cited_by_count":0,"area":"moe"},{"id":"2610.13328","title":"DuoRate: Two-Rate Per-Expert Precision Allocation for Mixture-of-Experts Serving","created":"2026-10-09","cited_by_count":0,"area":"moe"},{"id":"2610.13982","title":"PRIME: Frequency-Aware Unified Pruning and Merging for MoE Compression","created":"2026-09-23","cited_by_count":0,"area":"moe"}],"next_cursor":null}