{"total":69,"rows":[{"id":"2601.02780","title":"MiMo-V2-Flash Technical Report","created":"2026-01-06","cited_by_count":191,"area":"moe"},{"id":"2411.11217","title":"MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs","created":"2024-11-18","cited_by_count":73,"area":"moe"},{"id":"2510.11370","title":"Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers","created":"2025-10-13","cited_by_count":72,"area":"moe"},{"id":"2504.06792","title":"Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations","created":"2025-04-09","cited_by_count":16,"area":"moe"},{"id":"2509.17863","title":"Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving","created":"2025-09-22","cited_by_count":13,"area":"moe"},{"id":"2509.25041","title":"GRACE-MoE: Grouping and Replication with Locality-Aware Routing for Efficient Distributed MoE Inference","created":"2025-09-29","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":"2512.19849","title":"UCCL-EP: Portable Expert-Parallel Communication","created":"2025-12-22","cited_by_count":12,"area":"moe"},{"id":"2602.10693","title":"VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training","created":"2026-02-11","cited_by_count":11,"area":"moe"},{"id":"2505.03531","title":"Faster MoE LLM Inference for Extremely Large Models","created":"2025-05-06","cited_by_count":9,"area":"moe"},{"id":"2507.19017","title":"MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Cluster","created":"2025-07-25","cited_by_count":9,"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":"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":"2510.05497","title":"Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference","created":"2025-10-07","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":"2603.13606","title":"NCCL EP: Towards a Unified Expert Parallel Communication API for NCCL","created":"2026-03-13","cited_by_count":5,"area":"moe"},{"id":"2607.18722","title":"Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning","created":"2026-07-21","cited_by_count":5,"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":"2605.18643","title":"Post-Trained MoE Can Skip Half Experts via Self-Distillation","created":"2026-05-18","cited_by_count":4,"area":"moe"},{"id":"2508.19373","title":"HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference","created":"2025-08-26","cited_by_count":3,"area":"moe"},{"id":"2602.00800","title":"JTok: On Token Embedding as another Axis of Scaling Law via Joint Token Self-modulation","created":"2026-01-31","cited_by_count":3,"area":"moe"},{"id":"2605.08639","title":"ReLibra: Routing-Replay-Guided Load Balancing for MoE Training in Reinforcement Learning","created":"2026-05-09","cited_by_count":3,"area":"moe"},{"id":"2607.00466","title":"ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving","created":"2026-07-01","cited_by_count":3,"area":"moe"},{"id":"2607.13095","title":"Full-Pipeline Inference Optimization for MiMo-V2.5 Series: Pushing Hybrid SWA Efficiency to the Limit","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":"2508.03148","title":"Frontier: Simulating the Next Generation of LLM Inference Systems","created":"2025-08-05","cited_by_count":2,"area":"moe"},{"id":"2512.23995","title":"RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stress","created":"2025-12-30","cited_by_count":2,"area":"moe"},{"id":"2601.01310","title":"Making MoE-based LLM Inference Resilient with Tarragon","created":"2026-01-04","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":"2605.10670","title":"Surviving Partial Rank Failures in Wide Expert-Parallel MoE Inference","created":"2026-05-11","cited_by_count":2,"area":"moe"},{"id":"2606.11867","title":"Harnessing Routing Foresight for Micro-step-level MoE load balancing in RL Post-training","created":"2026-06-10","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":"2508.18376","title":"DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction","created":"2025-08-25","cited_by_count":1,"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":"2511.11505","title":"FarSkip-Collective: Unhobbling Blocking Communication in Mixture of Experts Models","created":"2025-11-14","cited_by_count":1,"area":"moe"},{"id":"2602.21626","title":"Multi-Layer Scheduling for MoE-Based LLM Reasoning","created":"2026-02-25","cited_by_count":1,"area":"moe"},{"id":"2604.17182","title":"Layer-wise MoE Routing Locality under Shared-Prefix Code Generation: Token-Identity Decomposition and Compile-Equivalent Fork Redundancy","created":"2026-04-19","cited_by_count":1,"area":"moe"},{"id":"2604.19503","title":"ReaLB: Real-Time Load Balancing for Multimodal MoE Inference","created":"2026-04-21","cited_by_count":1,"area":"moe"},{"id":"2605.09281","title":"TileQ: Efficient Low-Rank Quantization of Mixture-of-Experts with 2D Tiling","created":"2026-05-10","cited_by_count":1,"area":"moe"},{"id":"2606.00395","title":"PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning","created":"2026-05-29","cited_by_count":1,"area":"moe"},{"id":"2606.24506","title":"CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation","created":"2026-06-23","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":"2608.00916","title":"Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget","created":"2026-08-02","cited_by_count":1,"area":"moe"},{"id":"2608.02989","title":"AcceptMoE: Commitment-Weighted Self-Sizing Verifier Expert Sets for Efficient MoE Speculative Decoding","created":"2026-08-04","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":"2603.10031","title":"Architecture-Aware LLM Inference Optimization on AMD Instinct GPUs: A Comprehensive Benchmark and Deployment Study","created":"2026-02-27","cited_by_count":0,"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":"2604.26039","title":"RaMP: Runtime-Aware Megakernel Polymorphism for Mixture-of-Experts","created":"2026-04-28","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":"2605.06206","title":"Federation of Experts: Communication Efficient Distributed Inference for Large Language Models","created":"2026-05-07","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":"2605.21100","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":"2606.27866","title":"FlexMoE: One-for-All Nested Intra-Expert Pruning for MoE Language Models","created":"2026-06-26","cited_by_count":0,"area":"moe"},{"id":"2607.05116","title":"Communication-Aware Placement and Pruning for Efficient Mixture-of-Experts Inference","created":"2026-07-06","cited_by_count":0,"area":"moe"},{"id":"2607.23099","title":"Decoding the Skew: Distribution-Aware MoE Inference with Adaptive Kernel Dispatch","created":"2026-07-25","cited_by_count":0,"area":"moe"},{"id":"2608.21693","title":"Benchmarking Composable Compression Techniques in Mixture-of-Experts LLMs","created":"2026-08-22","cited_by_count":0,"area":"moe"},{"id":"2608.30567","title":"TuringLLM: Efficiently Scaling Foundation Models Toward Physical AI","created":"2026-08-31","cited_by_count":0,"area":"moe"},{"id":"2609.00791","title":"Instella-MoE Technical Report","created":"2026-09-01","cited_by_count":0,"area":"moe"},{"id":"2609.09748","title":"Epoch: Compiling Diffusion Blocks for Sparse MoE Serving","created":"2026-09-09","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":"2609.13537","title":"Dynamic HBM Repartitioning for Multi-Turn MoE Serving","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":"2609.36070","title":"Mixture-of-Kittens: MoE Megakernel for NVL72s","created":"2026-09-28","cited_by_count":0,"area":"moe"},{"id":"2609.40093","title":"Efficient Expert-Parallel Communication on PCIe-Connected Consumer GPUs","created":"2026-09-30","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":"2610.16890","title":"FORGE: Procedural Weight Generation for Sparse MoE Inference","created":"2026-10-12","cited_by_count":0,"area":"moe"},{"id":"2610.17959","title":"Virtual Head Attention","created":"2026-10-13","cited_by_count":0,"area":"moe"}],"next_cursor":null}