2 papers
cs.LG2026
DirMoE: Dirichlet-routed Mixture of Experts
Amirhossein Vahidi, Hesam Asadollahzadeh, Navid Akhavan Attar +4
Mixture-of-Experts (MoE) models have demonstrated exceptional performance in large-scale language models. Existing routers typically rely on non-differentiable Top-+Softmax, lim…
cs.CV2025
SIGMMA: Hierarchical Graph-Based Multi-Scale Multi-modal Contrastive Alignment of Histopathology Image and Spatial Transcriptome
Dabin Jeong, Amirhossein Vahidi, Ciro RamÃrez-Suástegui +11
Recent advances in computational pathology have leveraged vision-language models to learn joint representations of Hematoxylin and Eosin (HE) images with spatial transcriptomic (ST…