Preprint on interpolating between unnormalized densities: arxiv.org/abs/2301.07388 We introduce an objective for training continuous NFs without samples but with a given, non-normalized target energy that we can evaluate pointwise. Joint work with François Fleuret. (1/9)

There are densities for which a simple analytically defined interpolation from a normal results in mods "growing out of nowhere" instead of "sliding" there. This makes the transport field super hard to learn since it cannot just follow them.

Can you train GNNs without backprop? We extend the forward-forward algorithm to graph property prediction tasks, and the results are promising. Joint work with Mathieu @balintmate_ François Fleuret. arxiv.org/abs/2302.05282 1/N

Our paper "SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics" with François Fleuret, Daniele Paliotta, @balintmate_, Tobias Golling and others is accepted at #NeurIPS2023 Datasets and Benchmarks track. arxiv.org/abs/2202.05012 UNIGE_en

22 Unbelievable Places that are Hard to Believe Really Exist :D boredpanda.com/amazing-places/

Asking the right questions takes as much skill as giving the right answers. #copied

Napping is the best part of every day