Jaron Maene

email - scholar - github - bsky - linkedin

Hey there, I'm Jaron, a PhD candidate at the DTAI research group, supervised by Luc De Raedt. I do research in the intersection of probabilistic reasoning and deep learning (neurosymbolic AI).

News

June 25	This summer I'll be on a research internship at Basis.
February 25	Next semester I'll be at UCLA to visit Prof. Guy Van den Broeck.
January 25	Our work on speeding up arithmetic circuit evaluation on the GPU is accepted at ICLR25: "KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI" [paper][video][code].
December 24	Accepted at AAAI25: "The Gradient of Algebraic Model Counting" (Oral, top 4.6%) [paper][code].
June 24	"Extracting Finite State Machines from Transformers" was accepted at the Workshop on Mechanistic Interpretability at ICML2024 [paper].
May 24	"On the Hardness of Probabilistic Neurosymbolic Learning" was accepted at ICML24 [paper][video][code].
February 24	Attended the AI winter school at Paderborn University.
December 23	I presented my first paper at NeurIPS23: "Soft-Unification in Deep Probabilistic Programming" [paper][video][code].
January 23	Attended the DeepLearn 2023 Winter school.
December 20	I received a prize from IBM at the NLC2CMD competition at NeurIPS20, for my work on program synthesis with LLMs during a research internship at Bell Labs.

Appearances

November 24	Gave a talk a the StarAI lab at UCLA.
September 24	Presented two posters at the first NeSy conference.
July 24	I gave an invited seminar at the TU Wien Institute of Logic and Computation.
May 24	"Soft-Unification in Deep Probabilistic Logic", talk at the Generative NeSy Workshop.
	"Neurosymbolic Learning, a Probabilistic Journey", DTAI seminar [slides].
March 24	"AI and your Research", Invited talk (non-technical) at the LC&Y institute on the use of AI in research [video].
November 23	Presented a poster at the Flanders AI research day 2023.

Master Students

2025	Andres Van Schel. "An Evaluation of Current Mechanistic Interpretability Techniques on an Entailment Prediction Task in Propositional Logic with BERT"
2025	Andrei-Bogdan Florea. "Think before you Learn: Image Segmentation with Weak Supervision"
2025	Wout Seynaeve. "Learning from Logical Constraints: A Unifying approach for Weakly Supervised Semantic Segmentation"
2024	Rik Adriaensen. "Extracting Finite State Machines from Transformers"

Service

I have reviewed for JMLR, ICLR2025, and NeurIPS2025.

The preceding merely defines a way of thinking. But the point is to live.
- Albert Camus, Le Mythe de Sisyphe

Last updated: June, 2025.