{"total":20,"rows":[{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2404.07413","title":"JetMoE: Reaching Llama2 Performance with 0.1M Dollars","created":"2024-04-11","cited_by_count":57,"area":"moe"},{"id":"2410.07348","title":"MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts","created":"2024-10-09","cited_by_count":56,"area":"moe"},{"id":"2410.11842","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","created":"2024-10-15","cited_by_count":44,"area":"moe"},{"id":"2502.19261","title":"Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization","created":"2025-02-26","cited_by_count":24,"area":"moe"},{"id":"2507.07024","title":"FlexOlmo: Open Language Models for Flexible Data Use","created":"2025-07-09","cited_by_count":15,"area":"moe"},{"id":"2503.17793","title":"Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM","created":"2025-03-22","cited_by_count":13,"area":"moe"},{"id":"2512.23447","title":"Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss","created":"2025-12-29","cited_by_count":11,"area":"moe"},{"id":"2509.23678","title":"Towards a Comprehensive Scaling Law of Mixture-of-Experts","created":"2025-09-28","cited_by_count":10,"area":"moe"},{"id":"2410.10846","title":"Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models","created":"2024-10-01","cited_by_count":7,"area":"moe"},{"id":"2507.08771","title":"BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity","created":"2025-07-11","cited_by_count":6,"area":"moe"},{"id":"2509.25913","title":"Understanding the Mixture-of-Experts with Nadaraya-Watson Kernel","created":"2025-09-30","cited_by_count":6,"area":"moe"},{"id":"2605.08292","title":"Hierarchical Mixture-of-Experts with Two-Stage Optimization","created":"2026-05-08","cited_by_count":3,"area":"moe"},{"id":"2605.11689","title":"Slicing and Dicing: Configuring Optimal Mixtures of Experts","created":"2026-05-12","cited_by_count":2,"area":"moe"},{"id":"2609.11917","title":"Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Data","created":"2026-09-10","cited_by_count":2,"area":"moe"},{"id":"2510.26182","title":"MossNet: Mixture of State-Space Experts is a Multi-Head Attention","created":"2025-10-30","cited_by_count":0,"area":"moe"},{"id":"2602.11543","title":"Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm","created":"2026-02-12","cited_by_count":0,"area":"moe"},{"id":"2608.12419","title":"LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining","created":"2026-08-12","cited_by_count":0,"area":"moe"},{"id":"2609.35481","title":"TopoEP: Topology-Aware Load Balancing for Expert-Parallel MoE Training","created":"2026-09-28","cited_by_count":0,"area":"moe"},{"id":"2610.11317","title":"DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition","created":"2026-10-08","cited_by_count":0,"area":"moe"}],"next_cursor":null}