{"total":20,"rows":[{"id":"2406.05955","title":"Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters","created":"2024-06-10","cited_by_count":38,"area":"moe"},{"id":"2505.19645","title":"MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE","created":"2025-05-26","cited_by_count":19,"area":"moe"},{"id":"2506.20675","title":"Utility-Driven Speculative Decoding for Mixture-of-Experts","created":"2025-06-17","cited_by_count":13,"area":"moe"},{"id":"2510.10302","title":"SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference","created":"2025-10-11","cited_by_count":13,"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":"2603.06003","title":"EvoESAP: Non-Uniform Expert Pruning for Sparse MoE","created":"2026-03-06","cited_by_count":9,"area":"moe"},{"id":"2607.14647","title":"D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding","created":"2026-07-16","cited_by_count":5,"area":"moe"},{"id":"2602.09721","title":"Revealing the Challenges of Attention-FFN Disaggregation for Modern MoE Models and Hardware Systems","created":"2026-02-10","cited_by_count":4,"area":"moe"},{"id":"2604.10152","title":"SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding","created":"2026-04-11","cited_by_count":4,"area":"moe"},{"id":"2605.00342","title":"Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding","created":"2026-05-01","cited_by_count":4,"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":"2607.24434","title":"DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference","created":"2026-07-27","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":"2609.22156","title":"The Limits of Speculation: Bounding Speculative Decoding in Mixture-of-Experts","created":"2026-08-26","cited_by_count":1,"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":"2609.14237","title":"OpWeave: Flexible Operator Disaggregation for Heterogeneous LLM Serving","created":"2026-09-13","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":"2610.05774","title":"AdaSpark: Adaptive DSpark with Online Learning for Tree Verification and N-gram Fill","created":"2026-10-05","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}