{"total":53,"rows":[{"id":"2412.14711","title":"ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing","created":"2024-12-19","cited_by_count":54,"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":"2510.13999","title":"REAP the Experts: Why Pruning Prevails for One-Shot MoE compression","created":"2025-10-15","cited_by_count":44,"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":"2502.17298","title":"Delta Decompression for MoE-based LLMs Compression","created":"2025-02-24","cited_by_count":33,"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":"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":"2509.16105","title":"DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning","created":"2025-09-19","cited_by_count":26,"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":"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":"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":"2503.01359","title":"DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models","created":"2025-03-03","cited_by_count":10,"area":"moe"},{"id":"2508.05257","title":"MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs","created":"2025-08-07","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":"2508.02322","title":"CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis","created":"2025-08-04","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":"2602.09316","title":"Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density","created":"2026-02-10","cited_by_count":7,"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":"2606.15716","title":"How to Score Experts for One-Shot MoE Expert Pruning: A Unified Formulation and Selection Principle","created":"2026-06-14","cited_by_count":6,"area":"moe"},{"id":"2603.18492","title":"AIMER: Calibration-Free Task-Agnostic MoE Expert Pruning","created":"2026-03-19","cited_by_count":5,"area":"moe"},{"id":"2408.04307","title":"MoC-System: Efficient Fault Tolerance for Sparse Mixture-of-Experts Model Training","created":"2024-08-08","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":"2605.18643","title":"Post-Trained MoE Can Skip Half Experts via Self-Distillation","created":"2026-05-18","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":"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":"2604.20156","title":"Temporally Extended Mixture-of-Experts Models","created":"2026-04-22","cited_by_count":3,"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":"2510.10962","title":"MC#: Mixture Compressor for Mixture-of-Experts Large Models","created":"2025-10-13","cited_by_count":2,"area":"mllm"},{"id":"2602.04411","title":"Self-evolving Embodied AI","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2603.12645","title":"LightMoE: Reducing Mixture-of-Experts Redundancy through Expert Replacing","created":"2026-03-13","cited_by_count":2,"area":"moe"},{"id":"2604.06542","title":"Does a Global Perspective Help Prune Sparse MoEs Elegantly?","created":"2026-04-08","cited_by_count":2,"area":"moe"},{"id":"2605.30876","title":"dMoE: dLLMs with Learnable Block Experts","created":"2026-05-29","cited_by_count":2,"area":"moe"},{"id":"2505.17639","title":"PreMoE: Proactive Inference for Efficient Mixture-of-Experts","created":"2025-05-23","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":"2605.14438","title":"BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE","created":"2026-05-14","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":"2503.20138","title":"Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2601.14327","title":"Yuan3.0 Ultra: A Trillion-Parameter Enterprise-Oriented MoE LLM","created":"2026-01-20","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":"2606.09885","title":"TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts","created":"2026-06-03","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":"2607.08782","title":"Director: Accelerating Distributed MoE Serving via Online Proactive Expert Placement","created":"2026-06-13","cited_by_count":0,"area":"moe"},{"id":"2608.02940","title":"When Compression Scores Cannot Decide: Information Boundaries for Group-Robust LLM Pruning","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.05303","title":"EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding","created":"2026-08-05","cited_by_count":0,"area":"moe"},{"id":"2608.07890","title":"Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models","created":"2026-08-08","cited_by_count":0,"area":"moe"},{"id":"2608.10823","title":"MoE Proxy Models for Low-Cost Failure Reproduction and Diagnosis in LLM RL Post-Training","created":"2026-08-11","cited_by_count":0,"area":"moe"},{"id":"2609.06076","title":"Beyond Retraining-Free MoE Compression: A Cost-Normalized Study of Post-Compression Adjustment","created":"2026-09-05","cited_by_count":0,"area":"moe"},{"id":"2609.30465","title":"RAZOR: Pruning Replaceable Experts in LLMs","created":"2026-09-24","cited_by_count":0,"area":"moe"},{"id":"2609.36222","title":"BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding","created":"2026-09-28","cited_by_count":0,"area":"moe"},{"id":"2610.09342","title":"Shared Low-rank Basis Factorization for Data-free Mixture-of-Experts Compression","created":"2026-10-07","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}