Publications (56)
Latent Diffusion for Missing Data
Alberte Heering Estad, Ignacio Peis, Jes Frellsen
Diffusion models have emerged as powerful generative approaches for missing-data imputation, yet most existing methods operate directly in data space and degrade when training data…
The magnetic scalar potential for a rectangular prism
Berian James, Stefan Pollok, Jes Frellsen +1
We analytically solve Poisson's equation for the magnetic scalar potential generated by a uniformly magnetized rectangular prism and determine a closed-form solution for the magnet…
Learning Energy-Based Models by Self-normalising the Likelihood
Hugo Senetaire, Paul Jeha, Pierre-Alexandre Mattei +1
Training an energy-based model (EBM) with maximum likelihood is challenging due to the intractable normalisation constant. Traditional methods rely on expensive Markov chain Monte…
Normative Alignment of Recommender Systems via Internal Label Shift
Johannes Kruse, Kasper Lindskow, Michael Riis Andersen +4
We introduce NAILS (Normative Alignment of Recommender Systems via Internal Label Shift), a simple and scalable method for aligning recommendation outputs with target distributions…
The Multivariate Generalised von Mises distribution: Inference and applications
Alexandre K. W. Navarro, Jes Frellsen, Richard E. Turner
Circular variables arise in a multitude of data-modelling contexts ranging from robotics to the social sciences, but they have been largely overlooked by the machine learning commu…
Towards More General Control of Diffusion Models Using Jeffrey Guidance
Raphaël Razafindralambo, Rémy Sun, Frédéric Precioso +2
A key strength of diffusion models lies in their flexibility, since their outputs can be controlled at sampling time through guidance. However, beyond simple cases such as conditio…