Pauline Bourigault

photoPB(1).jpg

Hi! I am a PhD student at Imperial College London, working on robust machine learning, signal processing, and formal reasoning systems. My research focuses on scalable and interpretable learning algorithms for complex multi-dimensional data, with applications in time-series data, computer vision, and automated theorem proving.

I’m always interested in meeting new people and exploring new collaborations. If you’d like to get in touch with me, please email me at p.bourigault22 at imperial dot ac dot uk.

news

Mar 10, 2026 Excited to be part of Conception X Cohort 9. Grateful for the opportunity to turn research into real-world impact and connect with such an inspiring community.
Oct 20, 2025 Leveraging Frozen Pretrained Embeddings for Efficient Vision-Language Understanding accepted for oral presentation at ICCV Workshop on Safe and Trustworthy Multimodal AI Systems.
Jul 11, 2025 Presented my recent work on Information-Geometric Neural Granger Causality at ICML Workshop on High-dimensional Learning Dynamics.
Feb 01, 2025 Started contributing to Project Numina on formal reasoning and automated theorem proving.
Jan 15, 2025 Paper on using generalized hyperbolic processes for kernel-based anomaly detection will be at ICASSP 2025.
Aug 30, 2024 Will be presenting my recent paper on Multi-Modal Information Bottleneck Attribution with Cross-Attention Guidance at BMVC.
Jul 05, 2024 Gave a talk on Quaternion Recurrent Neural Network with Real-Time Learning at IJCNN, which builds on the generalized Hamiltonian–Real (GHR) calculus

selected publications

  1. FrEVL: Leveraging Frozen Pretrained Embeddings for Efficient Vision-Language Understanding
    Emmanuelle Bourigault and Pauline Bourigault
    In ICCV Workshop on Safe and Trustworthy Multimodal AI Systems, 2025
    Oral Presentation
    arXiv
  2. Kernel-Based Anomaly Detection Using Generalized Hyperbolic Processes
    Pauline Bourigault and Danilo P. Mandic
    In International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
    arXiv
  3. Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning
    Haiming Wang al.
    arXiv preprint arXiv:2504.11354, 2025
    arXiv
  4. Quaternion Recurrent Neural Network with Real-Time Learning and Maximum Correntropy
    Pauline Bourigault, Dongpo Xu, and Danilo P. Mandic
    In International Joint Conference on Neural Networks (IJCNN), 2024
    Oral Presentation
    arXiv
  5. Convex Quaternion Optimization for Signal Processing: Theory and Applications
    Shuli Sun, Qiankun Diao, Dongpo Xu, Pauline Bourigault, and Danilo P. Mandic
    IEEE Transactions on Signal Processing, 2023
    PDF