{"total":16,"rows":[{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073,"area":"moe"},{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152,"area":"moe"},{"id":"2410.13276","title":"SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs","created":"2024-10-17","cited_by_count":124,"area":"moe"},{"id":"2603.07685","title":"Scalable Training of Mixture-of-Experts Models with Megatron Core","created":"2026-03-08","cited_by_count":19,"area":"moe"},{"id":"2409.06669","title":"DA-MoE: Towards Dynamic Expert Allocation for Mixture-of-Experts Models","created":"2024-09-10","cited_by_count":15,"area":"moe"},{"id":"2505.00315","title":"Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing","created":"2025-05-01","cited_by_count":14,"area":"moe"},{"id":"2205.12399","title":"Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT","created":"2022-05-24","cited_by_count":12,"area":"moe"},{"id":"2508.06526","title":"PiKV: KV Cache Management System for Mixture of Experts","created":"2025-08-02","cited_by_count":5,"area":"moe"},{"id":"2601.01260","title":"MambaFormer: Token-Level Guided Routing Mixture-of-Experts for Accurate and Efficient Clinical Assistance","created":"2026-01-03","cited_by_count":1,"area":"moe"},{"id":"2509.10530","title":"Dynamic Adaptive Shared Experts with Grouped Multi-Head Attention Mixture of Experts","created":"2025-09-05","cited_by_count":0,"area":"moe"},{"id":"2604.02338","title":"LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning","created":"2026-02-01","cited_by_count":0,"area":"moe"},{"id":"2605.18848","title":"Exact Linear Attention","created":"2026-05-13","cited_by_count":0,"area":"moe"},{"id":"2607.06601","title":"TriRoute: Unified Learned Routing for Joint Adaptive Attention, Experts, and KV-Cache Allocation","created":"2026-07-07","cited_by_count":0,"area":"moe"},{"id":"2607.20981","title":"Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligence","created":"2026-07-23","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"}],"next_cursor":null}