{"total":16,"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":"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":"2509.08486","title":"Too Helpful, Too Harmless, Too Honest or Just Right?","created":"2025-09-10","cited_by_count":9,"area":"moe"},{"id":"2502.04416","title":"Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis","created":"2025-02-06","cited_by_count":8,"area":"moe"},{"id":"2507.06567","title":"SlimCaching: Edge Caching of Mixture-of-Experts for Distributed Inference","created":"2025-07-09","cited_by_count":7,"area":"moe"},{"id":"2602.14159","title":"Synergistic Intra- and Cross-Layer Regularization Losses for MoE Expert Specialization","created":"2026-02-15","cited_by_count":5,"area":"moe"},{"id":"2603.06626","title":"Grouter: Decoupling Routing from Representation for Accelerated MoE Training","created":"2026-02-22","cited_by_count":5,"area":"moe"},{"id":"2505.08944","title":"Toward Cost-Efficient Serving of Mixture-of-Experts with Asynchrony","created":"2025-05-13","cited_by_count":3,"area":"moe"},{"id":"2512.17073","title":"Bandwidth-Efficient Adaptive Mixture-of-Experts via Low-Rank Compensation","created":"2025-12-18","cited_by_count":3,"area":"moe"},{"id":"2602.03495","title":"DALI: A Workload-Aware Offloading Framework for Efficient MoE Inference on Local PCs","created":"2026-02-03","cited_by_count":2,"area":"moe"},{"id":"2602.07381","title":"When the Model Said 'No Comment', We Knew Helpfulness Was Dead, Honesty Was Alive, and Safety Was Terrified","created":"2026-02-07","cited_by_count":1,"area":"moe"},{"id":"2604.21330","title":"Teacher-Guided Routing for Sparse Vision Mixture-of-Experts","created":"2026-04-23","cited_by_count":0,"area":"moe"},{"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":"2608.26650","title":"Meta-Learning Where to Allocate Experts: Task-Conditioned Layer-Wise Compression for MoEs","created":"2026-08-27","cited_by_count":0,"area":"moe"},{"id":"2609.17940","title":"Beyond the Previous Layer: Residual Predictive Structure in Sparse MoE Routing","created":"2026-09-15","cited_by_count":0,"area":"moe"},{"id":"2610.12582","title":"One Model to Loop Them All: Elastic Latent Recurrence for Language Models","created":"2026-10-08","cited_by_count":0,"area":"moe"}],"next_cursor":null}