5 papers
Learning -Powered Conditional Distributions with Importance-Weighted Flow Matching
Maciej Falkiewicz, Frantzeska Lavda, Jason Ramapuram +1
Classifier-Free Guidance (CFG) with guidance scale is commonly motivated by the -powered conditional distribution obtained by setting , but CFG does not, in general, sa…
Hybrid Generative Modeling for Incomplete Physics: Deep Grey-Box Meets Optimal Transport
Gurjeet Sangra Singh, Maciej Falkiewicz, Alexandros Kalousis
Physics phenomena are often described by ordinary and/or partial differential equations (ODEs/PDEs), and solved analytically or numerically. Unfortunately, many real-world systems…
MING: A Functional Approach to Learning Molecular Generative Models
Van Khoa Nguyen, Maciej Falkiewicz, Giangiacomo Mercatali +1
Traditional molecule generation methods often rely on sequence- or graph-based representations, which can limit their expressive power or require complex permutation-equivariant ar…
Kolmogorov-Smirnov GAN
Maciej Falkiewicz, Naoya Takeishi, Alexandros Kalousis
We propose a novel deep generative model, the Kolmogorov-Smirnov Generative Adversarial Network (KSGAN). Unlike existing approaches, KSGAN formulates the learning process as a mini…
Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability
Maciej Falkiewicz, Naoya Takeishi, Imahn Shekhzadeh +4
Bayesian inference allows expressing the uncertainty of posterior belief under a probabilistic model given prior information and the likelihood of the evidence. Predominantly, the…