In August 2024, I started a PhD candidate position supervised by Jesse Read from École Polytechnique Paris at LIX, ORAILIX, backed by IRT SystemX and Safran in the scope of the JNI3 program.

Earlier, I cofounded Autoderm, focusing on developing AI models for dermatology concerns, which received the FDA breakthrough device designation in the USA, CE-marked Class I medical device (MDD) and MHRA device registered (UK). Previously, I served as a Rust developer at IoE Corp (formerly Quantum1Net) where we created a platform to run and distribute data services at the edge, received the IoT evolution product of the year award by TCM in 2021. I obtained a MSc and BSc from Maastricht University in Data Science & AI.

• September 2026 Paper accepted at NeurIPS 2026: “STEP: Learning STructured Embeddings for Progressive Time Series.”
• June 2026 🥈 Second place at Hack the World(s) with team Piaget.
  

  Latest news · June 2026

  Wiring the Fly Brain into a Hierarchical World Model

  A JEPA trained on the spikes of an embodied Drosophila connectome. Featured by Yann LeCun after Hack the World(s).

  Read the project → Discuss on LinkedIn ↗
• May 2026 Reward, or the Observation Stream? Auditing World Model Quality in RL on a Turbofan Substrate - RLxF workshop @ ICML 2026 in Seoul, South Korea
• April 2026 Paper accepted: “A Machine Learning Framework for Turbofan Health Estimation via Inverse Problem Formulation,” ECML PKDD 2026 in Naples, Italy.
• July 2026
  

  Workshop paper · July 2026

  TurboSens: auditing world-model quality in RL

  “Reward, or the Observation Stream?”, accepted at the RLxF workshop @ ICML 2026, Seoul.

  Read the paper →
• January to March 2026 École Polytechnique, Reinforcement Learning and Autonomous Agents. Crafted an RL turbofan degradation environment challenge with Jesse Read and Jérémie Decock.
• June 2025
  

  Paper accepted · June 2025

  Uncertainty Quantification as a Latent Health Indicator

  Complementary indicator for Remaining Useful Life prediction on turbofan engines, MIMAR 2025.

  Read the paper →
• May 2025 Paper accepted: “I-GLIDE: Input Groups for Latent health Indicators in Degradation Estimation,” ECML PKDD 2025.

• 6 months Eya Bradai, École Polytechnique, deep learning methods for complex system degradation modeling.
• 6 months Bahaeddine Abdessalem, École Polytechnique, deep learning methods for complex system degradation modeling.

• July 2026 ICML 2026, Seoul, South Korea.
• Sept 2025 ECML PKDD 2025, Porto, Portugal.
• 2025 MIMAR 2025, UQ for Turbofan engines.
• 21 Nov 2024 Digital Twins Design & Operations (DTD&O), Trocadéro, Paris.
• 18 Nov 2024 Symposium on Emerging Technologies for Reliability and Predictive Maintenance, CentraleSupélec.
• April 2024 ACM SIGAPP, Ávila, Spain.
• 2022 CES Las Vegas, IoT Evolution Product of the Year award by TCM.
• Fall 2021 Hyper Island, guest lecturer.

• 2026 🥈 Second place at Hack the World(s) with team Piaget: Wiring the Fly Brain into a Hierarchical World Model. Under the patronage of Philippe Baptiste and sponsored by Yann LeCun.
• 2026 Finalist at the Concours des Nouvelles Avancées on the theme “Intelligences?” with The Last Transmission, announced 20 May at the Panthéon, Paris.
• 2019 First prize at the IBM Quantum Challenge, with Maastricht University: an applied hybrid-quantum solution in generative design, culminating in a 3D-printed bike structure designed on IBM QX.
• to 2017 France national finswimming team: three national records, two international medals, fourth at the 2017 World Championship in Tomsk, Siberia.

I play the electric guitar, mostly V-shapes in the style of Alexi Laiho. Avid reader of classics and history, I take pleasure in visiting the places that inspired these works.

During my finswimming time I achieved some national records and international medals. In the 2017 World Championship in Tomsk, Siberia, I secured fourth in my highest-ranked race. Earlier I was part of Gilbert Gruss' karate school. I'm also terrible at yoga.

I also hold certifications in diving, lifeguarding, and apnea. The inspiration came from watching Star Wars: A New Hope at age five. X-Wing Starpilot or astronaut, ideally. Astronauts train in swimming pools, so it seemed like the right place to start.