{"total":25,"rows":[{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237,"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":"2408.04693","title":"Understanding the Performance and Estimating the Cost of LLM Fine-Tuning","created":"2024-08-08","cited_by_count":48,"area":"moe"},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47,"area":"moe"},{"id":"2505.22323","title":"Advancing Expert Specialization for Better MoE","created":"2025-05-28","cited_by_count":39,"area":"moe"},{"id":"2410.19034","title":"Mixture of Parrots: Experts improve memorization more than reasoning","created":"2024-10-24","cited_by_count":21,"area":"moe"},{"id":"2507.00029","title":"LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing","created":"2025-06-17","cited_by_count":18,"area":"moe"},{"id":"2504.00661","title":"DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism","created":"2025-04-01","cited_by_count":11,"area":"moe"},{"id":"2504.01337","title":"Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design","created":"2025-04-02","cited_by_count":6,"area":"moe"},{"id":"2410.03440","title":"Exploring the Benefit of Activation Sparsity in Pre-training","created":"2024-10-04","cited_by_count":5,"area":"moe"},{"id":"2408.04278","title":"LaDiMo: Layer-wise Distillation Inspired MoEfier","created":"2024-08-08","cited_by_count":4,"area":"moe"},{"id":"2605.12476","title":"Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts","created":"2026-05-12","cited_by_count":4,"area":"moe"},{"id":"2606.17952","title":"SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs","created":"2026-06-16","cited_by_count":4,"area":"moe"},{"id":"2601.03577","title":"Variational Inference, Entropy, and Orthogonality: A Unified Theory of Mixture-of-Experts","created":"2026-01-07","cited_by_count":3,"area":"moe"},{"id":"2604.00801","title":"Routing-Free Mixture-of-Experts","created":"2026-04-01","cited_by_count":2,"area":"moe"},{"id":"2604.06542","title":"Does a Global Perspective Help Prune Sparse MoEs Elegantly?","created":"2026-04-08","cited_by_count":2,"area":"moe"},{"id":"2605.06665","title":"UniPool: A Globally Shared Expert Pool for Mixture-of-Experts","created":"2026-05-07","cited_by_count":1,"area":"moe"},{"id":"2509.20073","title":"SHMoAReg: Spark Deformable Image Registration via Spatial Heterogeneous Mixture of Experts and Attention Heads","created":"2025-09-24","cited_by_count":0,"area":"moe"},{"id":"2602.14039","title":"Geometry-Preserving Aggregation for Mixture-of-Experts Embedding Models","created":"2026-02-15","cited_by_count":0,"area":"moe"},{"id":"2605.04058","title":"MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning","created":"2026-04-10","cited_by_count":0,"area":"moe"},{"id":"2606.08814","title":"STAR: Rethinking MoE Routing as Structure-Aware Subspace Learning","created":"2026-06-07","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":"2609.33090","title":"OneSign: Unifying Sign Language Understanding Tasks with One Model","created":"2026-09-27","cited_by_count":0,"area":"moe"},{"id":"2610.02584","title":"Dense Mixture-of-Experts as a Reparameterized Wide FFN: A Granularity Sweep at Fixed Compute","created":"2026-10-01","cited_by_count":0,"area":"moe"}],"next_cursor":null}