I am an AI Researcher at Together AI, where I work on research related to pretraining data for large language models. Previously, I obtained a PhD degree from ETH Zurich under the supervision of Prof. Ce Zhang. During my PhD my work revolved around robustness guarantees for machine learning systems. In addition, I have also made central contributions to the RedPajama Datasets.

I hold a BSc and an MSc in Mathematics, both from ETH Zürich, where I focused on mathematical statistics and machine learning and graduated in 2019 with a distinction.

Feel free to contact me by email, on Twitter or on LinkedIn.

Publications

• WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data
  Maurice Weber, Carlo Siebenschuh, Rory Butler, Anton Alexandrov, Valdemar Thanner, Georgios Tsolakis, Haris Jabbar, Ian Foster, Bo Li, Rick Stevens. In Advances in Neural Information Processing Systems, Volume 36, 2024.
  [Paper] [Code]
• RAB: Provable Robustness against Backdoor Attacks
  Maurice Weber, Xiaojun Xu, Bojan Karlaš, Ce Zhang, Bo Li. In 2023 IEEE Symposium on Security and Privacy (SP), 2023.
  [Paper] [Code]
• Predicting Properties of Quantum Systems with Conditional Generative Models
  Haoxiang Wang, Maurice Weber, Josh Izaac, Cedric Yen-Yu Lin. arXiv preprint arXiv:2211.16943, 2022.
  [Paper] [Code]
• Toward reliability in the nisq era: Robust interval guarantee for quantum measurements on approximate states
  Maurice Weber, Abhinav Anand, Alba Cervera-Lierta, Jakob S Kottmann, Thi Ha Kyaw, Bo Li, Alán Aspuru-Guzik, Ce Zhang, Zhikuan Zhao. In Physical Review Research, Volume 4, Issue 3, Article 033217, 2022, American Physical Society.
  [Paper] [Code]
• The AI Neuropsychologist: Automatic scoring of memory deficits with deep learning
  Nicolas Langer, Maurice Weber, Bruno Hebling Vieira, Dawid Strzelczyk, Lukas Wolf, Andreas Pedroni, Jonathan Heitz, Stephan Müller, Christoph Schultheiss, Marius Tröndle. On bioRxiv, 2022.06.15.496291, 2022, Cold Spring Harbor Laboratory.
  [Paper]
• Certifying Some Distributional Fairness with Subpopulation Decomposition
  Mintong Kang, Linyi Li, Maurice Weber, Yang Liu, Ce Zhang, Bo Li. In Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022.
  [Paper] [Code]
• Certifying Out-of-Domain Generalization for Blackbox Functions
  Maurice Weber, Linyi Li, Boxin Wang, Zhikuan Zhao, Bo Li, Ce Zhang. In 39th International Conference on Machine Learning (ICML), 2022.
  [Paper] [Code]
• Optimal provable robustness of quantum classification via quantum hypothesis testing
  Maurice Weber, Nana Liu, Bo Li, Ce Zhang, Zhikuan Zhao. In npj Quantum Information, Volume 7, Article 76, 2021, Nature Publishing Group UK London.
  [Paper]
• TSS: Transformation-Specific Smoothing for Robustness Certification
  Linyi Li, Maurice Weber, Xiaojun Xu, Luka Rimanic, Bhavya Kailkhura, Tao Xie, Ce Zhang, Bo Li. In 2021 ACM SIGSAC Conference on Computer and Communications Security (CCS), 2021.
  [Paper] [Code]
• Observer Dependent Lossy Image Compression
  Maurice Weber, Cedric Renggli, Helmut Grabner, Ce Zhang. In 42nd German Conference on Pattern Recognition (GCPR), 2020.
  [Paper] [Code]
• Towards device-agnostic mobile cough detection with convolutional neural networks
  Filipe Barata, Kevin Kipfer, Maurice Weber, Peter Tinschert, Elgar Fleisch, Tobias Kowatsch. In 2019 IEEE International Conference on Healthcare Informatics (ICHI), 2019.
  [Paper]