{"total":45,"rows":[{"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":"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":"2412.00099","title":"Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference","created":"2024-11-27","cited_by_count":14,"area":"moe"},{"id":"2602.16052","title":"MoE-Spec: Expert Budgeting for Efficient Speculative Decoding","created":"2026-02-17","cited_by_count":12,"area":"moe"},{"id":"2511.14102","title":"MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts","created":"2025-11-18","cited_by_count":11,"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":"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":"2512.13525","title":"Janus: Disaggregating Attention and Experts for Scalable MoE Inference","created":"2025-12-15","cited_by_count":8,"area":"moe"},{"id":"2508.12851","title":"Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement","created":"2025-08-18","cited_by_count":7,"area":"moe"},{"id":"2511.10054","title":"BuddyMoE: Exploiting Expert Redundancy to Accelerate Memory-Constrained Mixture-of-Experts Inference","created":"2025-11-13","cited_by_count":5,"area":"moe"},{"id":"2511.10676","title":"Pre-Attention Expert Prediction and Prefetching for Mixture-of-Experts Large Language Models","created":"2025-11-10","cited_by_count":4,"area":"moe"},{"id":"2601.21198","title":"ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling","created":"2026-01-29","cited_by_count":4,"area":"moe"},{"id":"2604.20156","title":"Temporally Extended Mixture-of-Experts Models","created":"2026-04-22","cited_by_count":3,"area":"moe"},{"id":"2605.27081","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","created":"2026-05-26","cited_by_count":3,"area":"moe"},{"id":"2606.15453","title":"A Spatio-Temporal Expert Prefetching Framework for Efficient MoE-based LLM Inference","created":"2026-06-13","cited_by_count":3,"area":"moe"},{"id":"2607.12696","title":"Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts","created":"2026-07-14","cited_by_count":3,"area":"moe"},{"id":"2608.16157","title":"FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution","created":"2026-08-17","cited_by_count":3,"area":"moe"},{"id":"2602.11192","title":"MELINOE: Fine-Tuning Enables Memory-Efficient Inference for Mixture-of-Experts Models","created":"2026-01-30","cited_by_count":2,"area":"moe"},{"id":"2604.18788","title":"Efficient Mixture-of-Experts LLM Inference with Apple Silicon NPUs","created":"2026-04-20","cited_by_count":2,"area":"moe"},{"id":"2604.23150","title":"Scaling Multi-Node Mixture-of-Experts Inference Using Expert Activation Patterns","created":"2026-04-25","cited_by_count":2,"area":"moe"},{"id":"2606.21868","title":"WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware","created":"2026-06-20","cited_by_count":2,"area":"moe"},{"id":"2607.08780","title":"Sticky Routing: Training MoE Models for Memory-Efficient Inference","created":"2026-06-12","cited_by_count":2,"area":"moe"},{"id":"2603.06350","title":"MoEless: Efficient MoE LLM Serving via Serverless Computing","created":"2026-03-06","cited_by_count":1,"area":"moe"},{"id":"2603.19289","title":"Speculating Experts Accelerates Inference for Mixture-of-Experts","created":"2026-03-09","cited_by_count":1,"area":"moe"},{"id":"2606.21428","title":"Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study","created":"2026-06-19","cited_by_count":1,"area":"moe"},{"id":"2608.18261","title":"Cacheable by Design? Training Mixture-of-Experts Routers for Locality Against the Edge Memory-Bandwidth Wall: A Pre-Registered Negative Result with a Systems Measurement Study","created":"2026-08-18","cited_by_count":1,"area":"moe"},{"id":"2604.02715","title":"FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving","created":"2026-04-03","cited_by_count":0,"area":"moe"},{"id":"2605.05899","title":"VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading","created":"2026-05-07","cited_by_count":0,"area":"moe"},{"id":"2607.24787","title":"SpecPrefetch: Parameter-Efficient Expert Prefetching for Sparse MoE Foundation Models","created":"2026-06-24","cited_by_count":0,"area":"moe"},{"id":"2608.00577","title":"HetRoute Heterogeneous and Cost-aware Collaborative Routing Framework for Distributed Edge MoE Inference","created":"2026-08-01","cited_by_count":0,"area":"moe"},{"id":"2608.07911","title":"Reproducible Evaluation of MoE Expert Caching: Replay Semantics, Workload Contamination, and Operating Regimes","created":"2026-08-08","cited_by_count":0,"area":"moe"},{"id":"2608.11688","title":"APEX: Adaptive Expert Prefetching for Memory-Efficient Edge MoE Inference","created":"2026-08-12","cited_by_count":0,"area":"moe"},{"id":"2608.15383","title":"Every Expert Counts: ExactMoE for Memory-Efficient W4A16 Inference","created":"2026-08-15","cited_by_count":0,"area":"moe"},{"id":"2609.06551","title":"EStream: Fast and Memory-Efficient MoE Prefill through Expert Virtualization on Mobile NPUs","created":"2026-09-06","cited_by_count":0,"area":"moe"},{"id":"2609.12978","title":"SeqMoE: Toward Full-Load Performance via Predictive and Graph-Compatible MoE Offloading","created":"2026-09-11","cited_by_count":0,"area":"moe"},{"id":"2609.13486","title":"Mixture-of-Experts Language Models Can Be Strong and Efficient Retrievers","created":"2026-09-11","cited_by_count":0,"area":"moe"},{"id":"2609.14643","title":"BigMoMo: Efficient Inference of Large-Scale MoE with Speculative Decoding on Mobile Devices","created":"2026-09-13","cited_by_count":0,"area":"moe"},{"id":"2609.18110","title":"SSD-LLaMA: SSD-Native Inference for Trillion-Parameter MoE at 1+ Token/s on a Consumer PC","created":"2026-09-16","cited_by_count":0,"area":"moe"},{"id":"2609.26061","title":"TopoCompress: Topology Aware Token Compression Algorithm for Distributed Edge MoE Inference","created":"2026-08-01","cited_by_count":0,"area":"moe"},{"id":"2609.33385","title":"OLED-MoE: Accelerating MoE-Based dLLM Inference via Inter-Iteration Locality-Aware Expert Offloading","created":"2026-09-27","cited_by_count":0,"area":"moe"},{"id":"2609.34077","title":"MaskCoFT: Masked Co-Adaptive Fine-Tuning for Memory-Efficient MoE Inference","created":"2026-09-28","cited_by_count":0,"area":"moe"},{"id":"2609.36301","title":"MoRE: Scaling mixture of experts with hardware-aware low-rank routing","created":"2026-09-28","cited_by_count":0,"area":"moe"},{"id":"2609.38090","title":"Mira: Memory-Efficient MoE Inference Using Adaptive Caching and Predictive Expert Staging","created":"2026-09-29","cited_by_count":0,"area":"moe"},{"id":"2610.09424","title":"Democratizing MoE inference on commodity GPUs with CoMoE","created":"2026-10-07","cited_by_count":0,"area":"moe"},{"id":"2610.15417","title":"SpecFit: Not All Draft Tokens Cost the Same in Offloaded MoE Inference","created":"2026-10-11","cited_by_count":0,"area":"moe"}],"next_cursor":null}