4 citations · 5 across the 6 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Hessian Geometry of Latent Space in Generative Models
Alexander Lobashev, Dmitry Guskov, Maria Larchenko +1
This paper presents a novel method for analyzing the latent space geometry of generative models, including statistical physics models and diffusion models, by reconstructing the Fi…
cs.LG2025
Covariant Gradient Descent
Dmitry Guskov, Vitaly Vanchurin
We present a manifestly covariant formulation of the gradient descent method, ensuring consistency across arbitrary coordinate systems and general curved trainable spaces. The opti…