3 papers
cs.LG2026
Reducing Memorisation in Generative Models via Riemannian Bayesian Inference
Johanna Marie Gegenfurtner, Albert Kjøller Jacobsen, Naima Elosegui Borras +2
Modern generative models can produce realistic samples, however, balancing memorisation and generalisation remains an open problem. We approach this challenge from a Bayesian persp…
stat.ML2025
VIKING: Deep variational inference with stochastic projections
Samuel G. Fadel, Hrittik Roy, Nicholas Krämer +5
Variational mean field approximations tend to struggle with contemporary overparametrized deep neural networks. Where a Bayesian treatment is usually associated with high-quality p…
cs.CV2023
Learning to Generate 3D Representations of Building Roofs Using Single-View Aerial Imagery
Maxim Khomiakov, Alejandro Valverde Mahou, Alba Reinders Sánchez +2
We present a novel pipeline for learning the conditional distribution of a building roof mesh given pixels from an aerial image, under the assumption that roof geometry follows a s…