Adrián Javaloy

University of Edinburgh

prof-pic.jpg

I am a postdoc at the April lab working with Dr. Antonio Vergari on robust and reliable probabilistic machine learning approaches.

I completed my PhD at the Probabilistic Machine Learning group working with Prof. Isabel Valera at Saarland University. Before that, I worked at the Max Planck Institute for Intelligent Systems in Tübingen at the Empirical Inference department and the Probabilistic Machine Learning group.

My research focuses on developing methods that are reliable, principled, and efficient. Loosely, I introduce inductive biases to models such that they comply with our expectations on how they should behave in the wild. My ultimate goal is to conduct interesting and principled research to better understand machine learning models and ease their deployment in the real-world.

news

Oct 24, 2025 Our latest work “DeCaFlow: A deconfounding causal generative model” has been accepted as a spotlight at NeurIPS 2025 💡
Mar 11, 2025 My dissertation was awarded with summa cum laude! 🎓
Oct 04, 2024 I have joined the april lab as a postdoc at the Universty of Edimburgh 🙈
Oct 01, 2024 I have submitted my PhD thesis :partying_face:
Dec 16, 2023 Causal NFs was accepted as an oral at NeurIPS 2023 :fire::fire: You can find the slides of my talk here.

selected publications

  1. Preprint
    COPA: Comparing the incomparable in multi-objective model evaluation
    Adrián Javaloy, Antonio Vergari, and Isabel Valera
    arXiv preprint arXiv:2503.14321, 2025
  2. DeCaFlow: A deconfounding causal generative model
    Alejandro Almodóvar*, Adrián Javaloy*, Juan Parras, and 2 more authors
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025
  3. Dissertation
    Meet my expectations: on the interplay of trustworthiness and deep learning optimization
    Adrián Javaloy
    2024
  4. Causal normalizing flows: from theory to practice
    Adrián Javaloy, Pablo Sánchez-Martín, and Isabel Valera
    In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, 2023