Minh-Khoi Nguyen-Nhat

Modeling Expert Interactions in Sparse Mixture of Experts via Graph Structures

Equivariant Metanetworks for Mixture-of-Experts Weights

Token Dynamics on Spheres in Mamba Models

Equivariant Neural Functional Networks for Transformers

Distance-Based Tree-Sliced Wasserstein Distance

Spherical Tree-Sliced Wasserstein Distance

Tree-Sliced Wasserstein Distance: A Geometric Perspective

Equivariant Polynomial Functional Networks

Projection Optimal Transport on Tree-Ordered Lines

Equivariant Polynomial Functional Networks