Duy-Tung Pham

Mixed-Curvature Tree-Sliced Wasserstein Distance

Tree-sliced Sobolev IPM

Revisiting Tree-Sliced Wasserstein Distance Through the Lens of the Fermat–Weber Problem

Equivariant Metanetworks for Mixture-of-Experts Weights

Token Dynamics on Spheres in Mamba Models

Demystifying the Token Dynamics of Deep Selective State Space Models

Equivariant Neural Functional Networks for Transformers

Dynamical Properties of Tokens in Self-Attention and Effects of Positional Encoding

Equivariant Polynomial Functional Networks

Equivariant Polynomial Functional Networks