Scholar
Jaron Maene
Google Scholar ID: leES0h0AAAAJ
KU Leuven
Citations & Impact
Citations
89
H-index
5
i10-index
4
Publications
8
Co-authors
3
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'Extracting Finite State Machines from Transformers' accepted at the Workshop on Mechanistic Interpretability at ICML2024; received an award from IBM at the NLC2CMD competition at NeurIPS20; published several papers such as 'Embeddings as Probabilistic Equivalence in Logic Programs', 'KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI', etc.; presented talks at various international conferences.
Research Experience
- Research internship at Basis, working on a probabilistic programming library called Weighted; will visit Prof. Guy Van den Broeck at UCLA next semester; attended the AI winter school at Paderborn University; participated in the DeepLearn 2023 Winter school.
Education
- PhD candidate at KU Leuven, supervised by Luc De Raedt
Background
- Research interests lie at the intersection of probabilistic reasoning and deep learning (neurosymbolic AI). His work involves machine learning models that exploit both data and (logical) knowledge, typically represented as logic programs and tractable circuits. He focuses on how to perform (exact/approximate) inference on these models and how to effectively optimize them.
Miscellany
- Advised master students Sam McManagan, Andrei-Bogdan Florea, Andres Van Schel, Wout Seynaeve, Rik Adriaensen; reviewed for JMLR, JAIR, ICLR25, and NeurIPS25.
