{"total":15,"rows":[{"id":"2410.07524","title":"Upcycling Large Language Models into Mixture of Experts","created":"2024-10-10","cited_by_count":49,"area":"moe"},{"id":"2411.00918","title":"LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models","created":"2024-11-01","cited_by_count":6,"area":"moe"},{"id":"2502.03044","title":"RepLoRA: Reparameterizing Low-Rank Adaptation via the Perspective of Mixture of Experts","created":"2025-02-05","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":"2501.18936","title":"Revisit Visual Prompt Tuning: The Expressiveness of Prompt Experts","created":"2025-01-31","cited_by_count":5,"area":"moe"},{"id":"2605.15403","title":"$\\phi$-Balancing for Mixture-of-Experts Training","created":"2026-05-14","cited_by_count":5,"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":"2605.02641","title":"Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE","created":"2026-05-04","cited_by_count":3,"area":"moe"},{"id":"2410.13964","title":"Sparse Mixture-of-Experts for Compositional Generalization: Empirical Evidence and Theoretical Foundations of Optimal Sparsity","created":"2024-10-17","cited_by_count":2,"area":"moe"},{"id":"2510.07205","title":"Guided by the Experts: Provable Feature Learning Dynamic of Soft-Routed Mixture-of-Experts","created":"2025-10-08","cited_by_count":2,"area":"moe"},{"id":"2505.18455","title":"On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts","created":"2025-05-24","cited_by_count":1,"area":"moe"},{"id":"2511.18493","title":"SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation","created":"2025-11-23","cited_by_count":1,"area":"moe"},{"id":"2605.02124","title":"Soft-to-Hard Routing in Sparse Mixture-of-Experts Models","created":"2026-05-04","cited_by_count":1,"area":"moe"},{"id":"2510.03151","title":"Mixture of Many Zero-Compute Experts: A High-Rate Quantization Theory Perspective","created":"2025-10-03","cited_by_count":0,"area":"moe"},{"id":"2610.15039","title":"Sparsity Saves Compute, Not Samples: Oracle Inequalities for Dense and Sparse Mixture of Experts","created":"2026-10-10","cited_by_count":0,"area":"moe"}],"next_cursor":null}