activity
20232026
most citedTransformers are Universal In-context Learners

2 citations · 4 across the 15 of their papers we have counts for

collaborators

22 papers

math.PR2026

Target-adapted Green-Bessel SVGD: uniform-in-time propagation of chaos and last-iterate consistency

Trevor Teolis, Maarten V. de Hoop

We prove uniform-in-time propagation of chaos and last-iterate consistency for a target-adapted Stein variational gradient descent (SVGD) flow on compact connected manifolds. The t…

math.AP2026

Generic Recovery of Permittivity and Permeability in Anisotropic Maxwell Systems

Antonio Cocan, Maarten V. de Hoop, Joonas Ilmavirta +2

We study the inverse problem of recovering the constitutive tensors of a homogeneous anisotropic electromagnetic medium without magnetoelectric coupling (non-chiral) from its Fresn…

math.AP2026

Riesz-Kernel Stein Variational Gradient Descent: Renormalized Entropy and Long-Time Particle Limits

Trevor Teolis, Maarten V. de Hoop

Stein variational gradient descent (SVGD) transports interacting particles toward a target distribution through deterministic kernelized dynamics. Singular Riesz kernels are attrac…

cs.LG2026

Function graph transformers universally approximate operators between function spaces

Takashi Furuya, David Mis, Ivan Dokmanić +2

We study the approximation of nonlinear operators between function spaces by transformers. Our approach is to lift functions to measures supported on their graphs and leverage a re…

math.OC2026

Training Infinitely Deep and Wide Transformers

Raphaël Barboni, Maarten V. de Hoop, Takashi Furuya +1

Transformers have become the dominant architecture in modern machine learning, yet the theoretical understanding of their training dynamics remains limited. This paper develops a r…

stat.ML2026

Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures

Lorenzo Baldassari, Josselin Garnier, Knut Solna +1

Obtaining stable diffusion-based samplers in high- and infinite-dimensional settings is challenging because errors can accumulate across high-frequency coordinates and make the dyn…