Research
👨🎓 I am a PhD student in Data Science at BMW Group associated with the University of Augsburg and advised by Pr. Dr. Rainer Lienhart.
🚗 Working on developing event sequence models alongside causal explaination for fault diagnostic in vehicles at BMW Group.
🔬 Research Focus: I bridge the gap between complex event sequences and causal reasoning to build reliable, explainable AI systems. My work focuses on Causal Discovery, Large Language Models (LLMs), and Neuro-Symbolic Logic applied to large-scale, high-dimensional vehicle diagnostic data.
⭐️ Open Source Software:
- 📦
seq2cause: A Python package for unifying population and sample-level causal discovery in high-dimensional event sequences via neural autoregressive density estimation.
💻 Tech Stack: PyTorch, Transformers, LLMs, Causal Discovery, Graph Representation Learning.
📢 I am actively seeking full-time Research Scientist/Machine Learning Engineer roles for 2026. Open to global relocation.
News
- March 2026: Two papers accepted to ICLR 2026 workshops! I will be presenting my work on multimodal vehicle diagnostics and neuro-symbolic LLMs virtually.
- Sept 2025: Two papers accepted to NeurIPS 2025 workshops (SPIGM & CauScien) in San Diego, USA.
- Feb 2025: Presented my work on event sensory data and language models at AAAI 2025.
Selected Publications
(For a full list, please see my Google Scholar)
-
Context-Informed Sequence Classification: A Multimodal Approach to Vehicle Diagnostics TSALM @ ICLR 2026 Hugo Math, Rainer Lienhart -
Neuro-Symbolic Rule Discovery: Empowering LLMs with Causality for Vehicle Diagnostics Logical Reasoning @ ICLR 2026 Hugo Math, Julian Lorenz, Rainer Lienhart -
One-Shot Multi-Label Causal Discovery in High-Dimensional Event Sequences CauScien @ NeurIPS 2025 Hugo Math, Robin Schön, Rainer Lienhart -
Harnessing Event Sensory Data for Error Pattern Prediction in Vehicles: A Language Model Approach AAAI 2025 Hugo Math, Rainer Lienhart, Robin Schön
Beyond Research
- 💡 Industry Experience: Multiple years as a freelance auto-entrepreneur engineering computer vision models to automate semiconductor wafer inspections.
- 🇸🇪 Global Perspective: Former Erasmus student at Chalmers University of Technology, Sweden.
I’m active on social media (Linkedin), happy to chat!