{"total":42,"rows":[{"id":"2507.19427","title":"Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding","created":"2025-07-25","cited_by_count":55,"area":"moe"},{"id":"2409.01141","title":"Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching","created":"2024-09-02","cited_by_count":34,"area":"moe"},{"id":"2404.05019","title":"Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts","created":"2024-04-07","cited_by_count":32,"area":"moe"},{"id":"2504.02263","title":"MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism","created":"2025-04-03","cited_by_count":32,"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":"2606.04101","title":"UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing","created":"2026-06-02","cited_by_count":9,"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":"2410.12247","title":"EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference","created":"2024-10-16","cited_by_count":6,"area":"moe"},{"id":"2503.09716","title":"MoE-Gen: High-Throughput MoE Inference on a Single GPU with Module-Based Batching","created":"2025-03-12","cited_by_count":6,"area":"moe"},{"id":"2512.09277","title":"Efficient MoE Serving in the Memory-Bound Regime: Balance Activated Experts, Not Tokens","created":"2025-12-10","cited_by_count":5,"area":"moe"},{"id":"2507.15465","title":"Rethinking LLM Inference Bottlenecks: Insights from Latent Attention and Mixture-of-Experts","created":"2025-07-21","cited_by_count":4,"area":"moe"},{"id":"2507.17133","title":"BrownoutServe: SLO-Aware Inference Serving under Bursty Workloads for MoE-based LLMs","created":"2025-07-23","cited_by_count":4,"area":"moe"},{"id":"2510.08055","title":"From Tokens to Layers: Redefining Stall-Free Scheduling for MoE Serving with Layered Prefill","created":"2025-10-09","cited_by_count":4,"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":"2504.09345","title":"MoE-Lens: Towards the Hardware Limit of High-Throughput MoE LLM Serving Under Resource Constraints","created":"2025-04-12","cited_by_count":3,"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":"2508.16700","title":"GPT-OSS-20B: A Comprehensive Deployment-Centric Analysis of OpenAI's Open-Weight Mixture of Experts Model","created":"2025-08-22","cited_by_count":2,"area":"moe"},{"id":"2605.02960","title":"MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving","created":"2026-05-03","cited_by_count":2,"area":"moe"},{"id":"2605.28302","title":"How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving","created":"2026-05-27","cited_by_count":2,"area":"moe"},{"id":"2510.19366","title":"MoE-Prism: Disentangling Monolithic Experts for Elastic MoE Services via Model-System Co-Designs","created":"2025-10-22","cited_by_count":1,"area":"moe"},{"id":"2606.00735","title":"ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving","created":"2026-05-30","cited_by_count":1,"area":"moe"},{"id":"2606.26607","title":"Moebius: Serving Mixture-of-Expert Models with Seamless Runtime Parallelism Switch","created":"2026-06-25","cited_by_count":1,"area":"moe"},{"id":"2607.18002","title":"ExpertPlex: A High-Goodput Disaggregated Serving System for MoE LLMs with Adaptive Persistent Kernels","created":"2026-07-20","cited_by_count":1,"area":"moe"},{"id":"2609.00993","title":"AInfer-PD: Communication-Safe In-Place Prefill-Decode Multiplexing for Distributed MoE Rollouts","created":"2026-09-01","cited_by_count":1,"area":"moe"},{"id":"2605.00254","title":"Rethinking Network Topologies for Cost-Effective Mixture-of-Experts LLM Serving","created":"2026-04-30","cited_by_count":0,"area":"moe"},{"id":"2605.11277","title":"Sieve: Dynamic Expert-Aware PIM Acceleration for Evolving Mixture-of-Experts Models","created":"2026-05-11","cited_by_count":0,"area":"moe"},{"id":"2605.17889","title":"CoX-MoE: Coalesced Expert Execution for High-Throughput MoE Inference with AMX-Enabled CPU-GPU Co-Execution","created":"2026-05-18","cited_by_count":0,"area":"moe"},{"id":"2605.19945","title":"GEM: GPU-Variability-Aware Expert to GPU Mapping for MoE Systems","created":"2026-05-19","cited_by_count":0,"area":"moe"},{"id":"2605.21100","title":"NanoCP: Request-Level Dynamic Context Parallelism for Data-Expert Parallel Decoding","created":"2026-05-20","cited_by_count":0,"area":"moe"},{"id":"2606.22541","title":"ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill","created":"2026-06-21","cited_by_count":0,"area":"moe"},{"id":"2607.02522","title":"Multi-Turn Distributed Inference with Mixture of Experts for 6G Edge--Cloud Networks","created":"2026-05-06","cited_by_count":0,"area":"moe"},{"id":"2607.13068","title":"The Economics of AI Decoding Chips: Rebalancing Compute, Capacity, and Bandwidth for Efficient LLM Inference","created":"2026-07-10","cited_by_count":0,"area":"moe"},{"id":"2608.04502","title":"AFD-Ledger: Deployment Provisioning for Attention--FFN Disaggregation","created":"2026-08-05","cited_by_count":0,"area":"moe"},{"id":"2608.13962","title":"MoE Expert Execution in Disaggregated LLM Serving with a High-Bandwidth ReRAM Near-Memory Architecture","created":"2026-08-14","cited_by_count":0,"area":"moe"},{"id":"2609.12550","title":"Quality-Constrained Routing over a Fixed Pool of Quantized Mixture-of-Experts Instances","created":"2026-09-11","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":"2609.21137","title":"A Multi-Engine Dataflow for MoE Decoding on Scratchpad-Based Tensor Accelerators","created":"2026-09-17","cited_by_count":0,"area":"moe"},{"id":"2609.34117","title":"SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving","created":"2026-09-28","cited_by_count":0,"area":"moe"},{"id":"2610.16890","title":"FORGE: Procedural Weight Generation for Sparse MoE Inference","created":"2026-10-12","cited_by_count":0,"area":"moe"},{"id":"2610.18010","title":"Fish Audio Drama 3 Technical Report","created":"2026-10-13","cited_by_count":0,"area":"moe"},{"id":"2610.18451","title":"FastEEP: Fast Intra-Instance Elastic Scaling for Expert-Parallel MoE Serving","created":"2026-10-13","cited_by_count":0,"area":"moe"}],"next_cursor":null}