{"total":20,"rows":[{"id":"2505.03804","title":"MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance","created":"2025-05-02","cited_by_count":34,"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":"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":"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":"2601.22101","title":"ECO: Quantized Training without Full-Precision Master Weights","created":"2026-01-29","cited_by_count":5,"area":"moe"},{"id":"2505.19427","title":"WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference","created":"2025-05-26","cited_by_count":3,"area":"moe"},{"id":"2509.25689","title":"Collaborative Compression for Large-Scale MoE Deployment on Edge","created":"2025-09-30","cited_by_count":3,"area":"moe"},{"id":"2608.30564","title":"Q-Strata: Hierarchical Bit Allocation for Mixed-Precision Quantization of Mixture-of-Experts LLMs","created":"2026-08-31","cited_by_count":3,"area":"moe"},{"id":"2608.11212","title":"Detecting a Route Flip Is Easier Than Knowing Whether to Fix It: Causal Route-Mediated Damage in Quantized Mixture-of-Experts","created":"2026-07-14","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":"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":"2601.13563","title":"ButterflyMoE: Compression-Scalable Ternary Experts via Structured Butterfly Orbits","created":"2026-01-20","cited_by_count":0,"area":"moe"},{"id":"2603.06746","title":"ButterflyViT: 354$\\times$ Expert Compression for Edge Vision Transformers","created":"2026-03-06","cited_by_count":0,"area":"moe"},{"id":"2604.10496","title":"CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts","created":"2026-04-12","cited_by_count":0,"area":"moe"},{"id":"2605.15572","title":"Measuring Maximum Activations in Open Large Language Models","created":"2026-05-15","cited_by_count":0,"area":"moe"},{"id":"2606.00079","title":"BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization","created":"2026-05-22","cited_by_count":0,"area":"moe"},{"id":"2608.08081","title":"RotaryQuant: Fitting 120B MoE Models on Consumer Hardware via Fused Compressed-Space Attention","created":"2026-08-08","cited_by_count":0,"area":"moe"},{"id":"2610.16890","title":"FORGE: Procedural Weight Generation for Sparse MoE Inference","created":"2026-10-12","cited_by_count":0,"area":"moe"}],"next_cursor":null}