Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling

Robert Gruhlke and three co-authors submitted the paper "Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling" to arXiv on July 7, 2026. The paper is referenced in ICML 2026 and falls under the stat.ML category. It explores the use of low-rank tensor train structures to improve score-based sampling in high-dimensional settings.