🧠 Mixture of Experts

🧠 NeurIPS2026 · 1 paper notes

SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization

SpecDrop shapes modular specialization through a fixed category-to-branch assignment, nonzero cross-category soft weights, and fixed-denominator merging, outperforming label-free matched controls on vision tasks with trusted inference-time category labels, while label-aware dense logit masking is more accurate and routing gains on fuzzy text partitions are near zero.