Based in Florence, Italy

Rodrigo Castellano Ontiveros

PhD researcher at the University of Siena.
Marie Skłodowska-Curie Fellow, LeMuR Project.

My research aims to make Neural-Symbolic reasoning both scalable and transparent. I leverage Reinforcement Learning for efficiency and build interpretable-by-design models grounded in first-order logic.

_

Journey

Rodrigo Castellano

Rodrigo Castellano Ontiveros

Marie Skłodowska-Curie Fellow

Research

AAAI 2026

DeepProofLog: Efficient Proving in Deep Stochastic Logic Programs

Y. Jiao*, R. Castellano Ontiveros*, L. De Raedt, M. Gori, F. Giannini, M. Diligenti, G. Marra
* Equal contribution

A novel NeSy system mapping the resolution process of Deep Stochastic Logic Programs to Markov Decision Processes, enabling efficient Reinforcement Learning for logic proving.

IJCAI 2025

Grounding Methods for Neural-Symbolic AI

R. Castellano Ontiveros, F. Giannini, M. Gori, G. Marra, M. Diligenti

Proposes a parameterized family of grounding methods generalizing Backward Chaining to control the trade-off between scalability and expressiveness.

XAI 2025

Interpretable Link Prediction via Neural-Symbolic Reasoning

Introduces interpretable-by-design R-CBM-style models that output explicit proof trees, evaluated using XAI metrics like coherence.

NeSy 2025

Distilling KGE Black Boxes into Interpretable NeSy Models

R. Castellano Ontiveros, F. Giannini, M. Diligenti

A framework to distill Knowledge Graph Embeddings into interpretable Neural-Symbolic models, ensuring high fidelity while providing logic proofs.

Nature Comms. 2024

Constructing Remote Photoplethysmogram Signals

R. Castellano Ontiveros, M. Elgendi, C. Menon

Developed a novel ML methodology that achieved SOTA performance in rPPG signal reconstruction from video, allowing the extraction of different physiological parameters.

J. Cheminf. 2024

Physicochemical modelling of the retention mechanism

Elena Bandini, Rodrigo Castellano Ontiveros, Ardiana Kajtazi, Hamed Eghbali, Frédéric Lynen

Applied Machine Learning algorithms to model the retention mechanisms in HPLC columns.

F. Physiol. 2023

Evaluating RGB channels in remote photoplethysmography

Rodrigo Castellano Ontiveros, Mohamed Elgendi, Giuseppe Missale, Carlo Menon

A comparative study of the efficacy of RGB channels in remote photoplethysmography (rPPG) when compared with contact-based PPG.

Academic
& Industry

Experience

Oct 2025 — Present

Visiting Researcher

Baker Hughes. Florence, Italy

Integrating logic reasoning systems with LLM agents.

Sep 2024 — Dec 2024

Visiting Researcher

KU Leuven. Leuven, Belgium

Developed DeepProofLog. Collaboration with Ying Jiao, Prof. Giuseppe Marra, and Prof. Luc De Raedt.

Apr 2023 — Oct 2023

Trainee

ING Bank. Brussels, Belgium

International Talent Programme. Rotational data science/analytics graduate program.

Oct 2022 — Feb 2023

Master Thesis Researcher

ETH Zürich. Zürich, Switzerland

rPPG extraction from video. Awarded Karl Engver's Foundation Grant. Supervised by Prof. Carlo Menon and Prof. Moe Elgendi.

Nov 2021 — Apr 2022

Teaching Assistant

KTH Royal Institute of Technology. Stockholm, Sweden

Supported courses in Artificial Intelligence (DD2380) and Machine Learning (DD2421).

Oct 2020 — Jun 2021

AI Applied Scientist

Desion, Franunhofer Institute. Darmstadt, Germany

Built automated visual inspection systems with Computer Vision models (Mask R-CNN, Faster R-CNN) using synthetic data. Synthetic data created with Unreal Engine.

Education

Nov 2023 — Present

PhD Researcher in AI

University of Siena. Siena, Italy

Marie Skłodowska-Curie Fellow. Project LeMuR: Learning with Multiple Representations. Supervisors: Prof. Marco Gori, Prof. Michelangelo Diligenti, Dr. Francesco Giannini.

Apr 2021 — Apr 2023

MSc in Machine Learning

KTH Royal Institute of Technology. Stockholm, Sweden
Sep 2021 — Mar 2022

Exchange Student

RWTH Aachen University. Aachen, Germany
Sept 2018 — Jun 2019

Exchange Bachelor Student

University of Helsinki. Helsinki, Finland
Oct 2015 — Nov 2020

BSc in Physics

University of Granada. Granada, Spain.

Participation & Dissemination

Aug 2025

IJCAI 2025

Montreal, Canada

Poster & Oral: Grounding Methods for Neural-Symbolic AI

Aug 2025

NeSy 2025

Santa Cruz, US

Poster: Distilling KGE black boxes into interpretable NeSy models

July 2025

XAI 2025

Istanbul, Turkey

Oral: Interpretable Link Prediction via Neural-Symbolic Reasoning

June 2025

SMiLe 2025

The Netherlands

Poster: Scalable grounding and explainable NeSy methods

Mar 2025

Winter School

Umeå, Sweden

Poster: Explainability in FOL-based models

July 2024

Summer School

Athens, Greece

Participant

Feb 2024

Winter School

Paderborn, Germany

Poster: Grounding Methods in NeSy