Tho Tran Huu

Discontinuities in Sparse Mixture-of-Experts: A Measure-Stochastic Analysis

Equivariant Metanetworks for Mixture-of-Experts Weights

Equivariant Neural Functional Networks for Transformers

Equivariant Polynomial Functional Networks

Tree-Sliced Wasserstein Distance: A Geometric Perspective

Projection Optimal Transport on Tree-Ordered Lines

Equivariant Polynomial Functional Networks

L-MSA: Layer-wise Fine-tuning using the Method of Successive Approximations