Viktor Stein (@viktorajstein)

Score Learning under the Manifold Hypothesis: Theory and Implications for Data Science

Convergence theory and application of distribution optimization: Non-convexity, particle approximation, and diffusion models

Preconditioned Sampling and Sparse Transformer Architectures from Regularized Wasserstein Proximal Operators

Transport Information Geometric Computation Year 3

The mathematics of transformers

Computational OT #4 - Gradient flow and diffusion models