51 citations · 56 across the 13 of their papers we have counts for
7 papers · 1 filter
Logical Guidance for the Exact Composition of Diffusion Models
Francesco Alesiani, Jonathan Warrell, Tanja Bien +3
We propose LOGDIFF (Logical Guidance for the Exact Composition of Diffusion Models), a guidance framework for diffusion models that enables principled constrained generation with c…
Variational Kolmogorov-Arnold Network
Francesco Alesiani, Henrik Christiansen, Federico Errica
Kolmogorov-Arnold Networks (KANs) offer a theoretically grounded alternative to multi-layer perceptrons by representing multivariate functions as compositions of univariate basis f…
Geometric Kolmogorov-Arnold Superposition Theorem
Francesco Alesiani, Takashi Maruyama, Henrik Christiansen +1
The Kolmogorov-Arnold Theorem (KAT), or more generally, the Kolmogorov Superposition Theorem (KST), establishes that any non-linear multivariate function can be exactly represented…
Adaptive Width Neural Networks
Federico Errica, Henrik Christiansen, Viktor Zaverkin +2
For almost 70 years, researchers have typically selected the width of neural networks' layers either manually or through automated hyperparameter tuning methods such as grid search…
Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
Viktor Zaverkin, Francesco Alesiani, Takashi Maruyama +5
The ability to perform fast and accurate atomistic simulations is crucial for advancing the chemical sciences. By learning from high-quality data, machine-learned interatomic poten…
Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching
Federico Errica, Henrik Christiansen, Viktor Zaverkin +3
Long-range interactions are essential for the correct description of complex systems in many scientific fields. The price to pay for including them in the calculations, however, is…
Continual Invariant Risk Minimization
Francesco Alesiani, Shujian Yu, Mathias Niepert
Empirical risk minimization can lead to poor generalization behavior on unseen environments if the learned model does not capture invariant feature representations. Invariant risk…