{"total":16,"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":"2512.14080","title":"SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations","created":"2025-12-16","cited_by_count":21,"area":"moe"},{"id":"2512.19849","title":"UCCL-EP: Portable Expert-Parallel Communication","created":"2025-12-22","cited_by_count":12,"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":"2508.09591","title":"HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap","created":"2025-08-13","cited_by_count":4,"area":"moe"},{"id":"2603.02731","title":"Practical FP4 Training for Large-Scale MoE Models on Hopper GPUs","created":"2026-03-03","cited_by_count":2,"area":"moe"},{"id":"2506.02965","title":"PC-MoE: Memory-Efficient and Privacy-Preserving Collaborative Training for Mixture-of-Experts LLMs","created":"2025-06-03","cited_by_count":1,"area":"moe"},{"id":"2511.02302","title":"FP8-Flow-MoE: A Casting-Free FP8 Recipe without Double Quantization Error","created":"2025-11-04","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":"2605.05607","title":"Accelerating MoE with Dynamic In-Switch Computing on Multi-GPUs","created":"2026-05-07","cited_by_count":0,"area":"moe"},{"id":"2605.15572","title":"Measuring Maximum Activations in Open Large Language Models","created":"2026-05-15","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":"2605.23294","title":"NASiC: 3D NAND-based CAM-Selected Multibit CIM Architecture for Efficient On-Device Mixture-of-Experts LLM Inference","created":"2026-05-22","cited_by_count":0,"area":"moe"},{"id":"2607.06202","title":"UBEP: Re-architecting Expert Parallelism Communication Library for Production Superpods","created":"2026-07-07","cited_by_count":0,"area":"moe"},{"id":"2608.14385","title":"DeaMoE: Efficient MoE Structure for Fast Small-Batch Decoding","created":"2026-08-14","cited_by_count":0,"area":"moe"},{"id":"2608.27874","title":"TerraceMoE: A Cost Model for Hierarchical MoE All-to-All Communication","created":"2026-08-28","cited_by_count":0,"area":"moe"}],"next_cursor":null}