2 papers
cs.CV2026
bViT: Investigating Single-Block Recurrence in Vision Transformers for Image Recognition
Michal Byra, Pawel Olszowiec, Grzegorz Stefanski +2
Vision Transformers (ViTs) are built by stacking independently parameterized blocks, but it remains unclear how much of this depth requires layer specific transformations and how m…
cs.GR2025
Beyond Blur: A Fluid Perspective on Generative Diffusion Models
Grzegorz Gruszczynski, Jakub Meixner, Michal Jan Wlodarczyk +1
We propose a novel PDE-driven corruption process for generative image synthesis based on advection-diffusion processes which generalizes existing PDE-based approaches. Our forward…