AWehenkel

UMNN

Implementation of Unconstrained Monotonic Neural Network and the related experiments. These architectures are particularly useful for modelling monotonic transformations in normalizing flows.

Graphical-Normalizing-Flows

Combining smooth constraint for building DAG with normalizing flow in order to replace autoregressive transformations while keeping tractable Jacobian.

Normalizing-Flows

This repository offers an implementation of some common architectures for normalizing flows.

generalized-UMNN

Extension to multivariate unconstrained monotonic functions.

phd-thesis

My baby.

best-twitter-threads

LatentDiffusion

# Research project on hidden markov models for diffusion on images

NTDS-Project

ADA-2017

Repository containing project and homeworks of the ADA course

AffineFlowCausalInf

Code for "Autoregressive flow-based causal discovery and inference" - ICML INNF workshop, 2020

AIAP1

Project 1 of machine learning

AWehenkel.github.io

Personal Website

compiler

constraint_prog

cp-DO

ffjord

code for "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models".

fish-app

info8004-advanced-machine-learning

Lectures for INFO8004 - Advanced Machine Learning, ULiège

info8010-deep-learning

Lectures for INFO8010 - Deep Learning, ULiège

Logic_project

MongeAmpereFlow

Continuous-time gradient flow for generative modeling and variational inference

nflows

Normalizing flows in PyTorch

oose

OOSE_2

openBF

1D blood flow model

openBF-db

openBF population generator

ott

Optimal Transport tools implemented with the JAX framework, to get auto-diff, parallel and jit-able computations.

phd-defense

pytorch-examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

torchdiffeq

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.