{"total":43,"rows":[{"id":"2308.14352","title":"EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices","created":"2023-08-28","cited_by_count":69,"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":"2411.01016","title":"MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition","created":"2024-11-01","cited_by_count":57,"area":"moe"},{"id":"2411.01433","title":"HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference","created":"2024-11-03","cited_by_count":55,"area":"moe"},{"id":"2407.00945","title":"Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs","created":"2024-07-01","cited_by_count":53,"area":"moe"},{"id":"2410.06270","title":"Mixture Compressor for Mixture-of-Experts LLMs Gains More","created":"2024-10-08","cited_by_count":41,"area":"moe"},{"id":"2310.18859","title":"SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models","created":"2023-10-29","cited_by_count":38,"area":"moe"},{"id":"2409.06211","title":"STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning","created":"2024-09-10","cited_by_count":30,"area":"moe"},{"id":"2406.02500","title":"Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques","created":"2024-06-04","cited_by_count":24,"area":"moe"},{"id":"2404.01365","title":"Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation","created":"2024-04-01","cited_by_count":21,"area":"moe"},{"id":"2504.05586","title":"Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations","created":"2025-04-08","cited_by_count":20,"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":"2504.06792","title":"Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations","created":"2025-04-09","cited_by_count":16,"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":"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":"2412.00069","title":"Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning","created":"2024-11-26","cited_by_count":10,"area":"moe"},{"id":"2501.15316","title":"ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning","created":"2025-01-25","cited_by_count":10,"area":"moe"},{"id":"2505.05950","title":"FloE: On-the-Fly MoE Inference on Memory-constrained GPU","created":"2025-05-09","cited_by_count":9,"area":"moe"},{"id":"2511.04805","title":"PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference","created":"2025-11-06","cited_by_count":9,"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":"2512.18425","title":"MoE Pathfinder: Trajectory-driven Expert Pruning","created":"2025-12-20","cited_by_count":7,"area":"moe"},{"id":"2507.08771","title":"BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity","created":"2025-07-11","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":"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":"2505.18451","title":"$\\mu$-MoE: Test-Time Pruning as Micro-Grained Mixture-of-Experts","created":"2025-05-24","cited_by_count":3,"area":"moe"},{"id":"2604.20156","title":"Temporally Extended Mixture-of-Experts Models","created":"2026-04-22","cited_by_count":3,"area":"moe"},{"id":"2408.11855","title":"FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models","created":"2024-08-15","cited_by_count":2,"area":"moe"},{"id":"2504.04342","title":"Pruning Laws for Large Language Models","created":"2025-04-06","cited_by_count":2,"area":"moe"},{"id":"2506.00965","title":"FLEx: Personalized Federated Learning for Mixture-of-Experts LLMs via Expert Grafting","created":"2025-06-01","cited_by_count":2,"area":"moe"},{"id":"2607.08601","title":"It Takes a MAESTRO To Prune Bad Experts","created":"2026-07-09","cited_by_count":2,"area":"moe"},{"id":"2502.02040","title":"M2R2: Mixture of Multi-Rate Residuals for Efficient Transformer Inference","created":"2025-02-04","cited_by_count":1,"area":"moe"},{"id":"2511.19480","title":"Exploiting the Experts: Unauthorized Compression in MoE-LLMs","created":"2025-11-22","cited_by_count":1,"area":"moe"},{"id":"2605.13997","title":"HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts","created":"2026-05-13","cited_by_count":1,"area":"moe"},{"id":"2605.28207","title":"Pruning and Distilling Mixture-of-Experts into Dense Language Models","created":"2026-05-27","cited_by_count":1,"area":"moe"},{"id":"2608.15299","title":"MAPLE: MoE Adaptive Plug-and-play Layer-wise Expert allocation","created":"2026-08-15","cited_by_count":1,"area":"moe"},{"id":"2602.15521","title":"ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation Patterns","created":"2026-02-17","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":"2603.20492","title":"AE-LLM: Adaptive Efficiency Optimization for Large Language Models","created":"2026-03-20","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":"2609.31631","title":"OMP-MoE: Efficient Expert Pruning for Mixture-of-Experts LLMs via Orthogonal Matching Pursuit","created":"2026-09-09","cited_by_count":0,"area":"moe"},{"id":"2610.00367","title":"MoRA: MoE Pruning via Router Bias Learning and Expert Approximation","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":"2610.19232","title":"Spectral-MoE: Heterogeneous Per-Layer Expert Utilization in Dense-to-MoE Conversion","created":"2026-10-13","cited_by_count":0,"area":"moe"}],"next_cursor":null}