← Search

Yilong Fan

2 accepted papers

2025

Maximum Score Routing For Mixture-of-Experts

ACL 2025finding

Routing networks in sparsely activated mixture-of-experts (MoE) dynamically allocate input tokens to top-k experts through differentiable sparse transformations, enabling scalable model capacity while preserving computational efficiency. Traditional MoE networks impose an expert capacity constraint…

2024

Balanced And Discriminative Contrastive Learning For Class-Imbalanced Medical Images

ICASSP 2024accepted

The class imbalance problem, which is prevalent in medical image datasets, seriously affects the diagnostic effectiveness of deep learning-based network models. Recently, the method based on two-stage learning has produced promising results in solving class imbalance. In two-stage learning, the lear…

Cited by 0SourceScholar