【论文】LatentLoop：利用非对称计算分配扩展循环MoE模型

arXiv 2610.19975 · 24 人推荐 · 附代码 lcqysl/LatentLoop（1 stars）。Looped Mixture-of-Experts (MoE) models combine parameter reuse with sparse computation to improve performance under matched budgets. Prior work demonstrates that different loop visits can play different roles even when they share parameters. To probe the contributions of different loop visits, we learn separate residual coefficients in a model that applies a shared block twice, observing a smaller scale in the first visit. Fixed coefficient experiments show that reducing the first visit's scale