Chair for Machine Learning & Computer Vision

  1. University
  2. Faculties
  3. Faculty of Applied Computer Science
  4. Institute of Computer Science
  5. Chairs and Professors
  6. Machine Learning & Computer Vision
  7. Team
  8. Hugo Math

Hugo Math

Externer Doktorand
Chair for Machine Learning & Computer Vision
Phone: +49 (821) 598 4386
Email:
Room: 1025 (N)
Address: Universitätsstraße 6a, 86159 Augsburg

CV

Lebenslauf:

  • 2023 - Now: PhD candidate in Deep learning at University of Augsburg and BMW Promotion program
  • 2022 - 2023: Master of Business Administration at IAE Dijon
  • 2018 - 2023: Master of Science in Engineering at Polytech Dijon (University of Burgundy)
 
Areas of interest:
  • Deep Learning applied to machine generated data
  • Self-supervised learning
  • Sequence classification
 
 
About me:
I am currently a PhD candidate at the University of Augsburg and part of the BMW promotion program. My main research area focuses on how to leverage machine generated data from cars with deep learning methods to automize defects detection. This involves NLP based models, sequence classification and unsupervised learning in a big data environment.
 

Publications

2026 | 2025

2026

Hugo Math and Rainer Lienhart. 2026. Context-informed sequence classification: a multimodal approach to vehicle diagnostics. In 1st ICLR Workshop on Time Series in the Age of Large Models (ICLR 2026 TSALM Workshop), 26 April 2026, Rio de Janeiro, Brazil. OpenReview.net, Amherst, MA
PDF | BibTeX | RIS | URL

Hugo Math, Julian Lorenz and Rainer Lienhart. in press. Neuro-symbolic rule discovery: empowering LLMs with causality for vehicle diagnostics. In ICLR 2026 Workshop on Logical Reasoning of Large Language Models, 26 April 2026, Rio de Janeiro, Brazil. OpenReview.net, Amherst, MA
BibTeX | RIS | URL

Hugo Math and Rainer Lienhart. in press. Your autoregressive model already reveals the causal graph. In ICML 2026 Workshop on Structured Probabilistic Inference & Generative Modeling (SPIGM), 10-11 July 2026, Seoul, South Korea.
BibTeX | RIS | URL

2025

Hugo Math, Rainer Lienhart and Robin Schön. 2025. Harnessing event sensory data for error pattern prediction in vehicles: a language model approach. Proceedings of the AAAI Conference on Artificial Intelligence 39, 18, 19423-19431. DOI: 10.1609/aaai.v39i18.34138
PDF | BibTeX | RIS | DOI

Hugo Math, Robin Schön and Rainer Lienhart. 2025. One-shot multi-label causal discovery in high-dimensional event sequences. In NeurIPS 2025 Workshop on CauScien: Uncovering Causality in Science, 6 December 2025, San Diego, CA, USA.
PDF | BibTeX | RIS | URL

Hugo Math and Rainer Lienhart. 2025. Towards practical multi-label causal discovery in high-dimensional event sequences via one-shot graph aggregation. In NeuRIPS2025 Workshop on Structured Probabilistic Inference & Generative Modeling: Probabilistic Inference in the Era of Large Foundation Models, 6 December 2025, San Diego, CA, USA. DOI: 10.48550/arXiv.2509.19112
PDF | BibTeX | RIS | DOI

Search