I am currently working as a postdoctoral researcher at Bern University of Applied Sciences (BFH) in the Energy, Weather and AI group. My research focuses on the short-term forecasting of solar production based on geostationary satellite images.


During my PhD, I worked on representation learning for images at IRISA in Vannes under the supervision of Minh-Tan Pham and Nicolas Courty. Prior to joining IRISA, I graduated from the Université de Technologie de Compiègne (UTC).


Other interests include Open Source contributions, outdoor sports (running, biking, swimming, climbing) and drawing.

Notes My resume 🎈 Notebooks

Publications

2026

  1. DJ4Oceananigans: A differentiable, Julia-based ocean general circulation model for gradient-based parameter calibration, online learning and variational data assimilation

    27/02/2026  ·  Joseph Kump, William Moses, Gregory Wagner, Dhruv Apte, Valentin Churavy, Christopher N Hill, Paul Berg, …

2025

  1. DJ4Earth: Differentiable, and Performance-portable Earth System Modeling via Program Transformations

    14/11/2025  ·  Journal of Advances in Modeling Earth Systems (JAMES)  ·  William S Moses, Gong Cheng, Valentin Churavy, Maximilian Gelbrecht, Milan Klöwer, Joseph Kump, Mathieu Morlighem, Sarah Williamson, Dhruv Apte, Paul Berg, …

  2. Multi-Prototype Hyperbolic Learning Guided by Class Hierarchy

    22/08/2025  ·  International Journal of Computer Vision (IJCV)  ·  Paul Berg, Léo Buecher, Björn Michele, Minh-Tan Pham, Laetitia Chapel, Nicolas Courty

2024

  1. Contributions to Representation Learning in Computer Vision and Remote Sensing

    13/12/2024  ·  Paul Berg

  2. Horospherical Learning with Smart Prototypes

    25/11/2024  ·  British Machine Vision Conference (BMVC)  ·  Paul Berg, Björn Michele, Minh-Tan Pham, Laetitia Chapel, Nicolas Courty

  3. Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning

    27/11/2024  ·  British Machine Vision Conference (BMVC)  ·  Hoang-Ân Lê, Paul Berg, Minh-Tan Pham

  4. Multimodal Supervised Contrastive Learning in Remote Sensing Downstream Tasks

    15/04/2024  ·  IEEE Geoscience and Remote Sensing Letters (GRSL)  ·  Paul Berg, Baki Uzun, Minh-Tan Pham, Nicolas Courty

2023

  1. Joint multi-modal Self-Supervised pre-training in Remote Sensing: Application to Methane Source Classification

    19/06/2023  ·  IGARSS  ·  Paul Berg, Minh-Tan Pham, Nicolas Courty

  2. Spherical Sliced Wasserstein

    01/05/2023  ·  International Conference on Learning Representations (ICLR)  ·  Clément Bonet, Paul Berg, Nicolas Courty, Lucas Drumetz, François Septier, Minh-Tan Pham

  3. Automatic part segmentation of facial anatomies using geometric deep learning toward a computer-aided facial rehabilitation

    01/03/2023  ·  Duc-Phong Nguyen, Paul Berg, Bilel Debbabi, Tan-Nhu Nguyen, Vi-Do Tran, Ho-Quang Nguyen, Stéphanie …

2022

  1. Self-Supervised Learning for Scene Classification in Remote Sensing: Current State of the Art and Perspectives

    17/08/2022  ·  Remote Sensing  ·  Paul Berg, Minh-Tan Pham, Nicolas Courty

  2. Weakly Supervised Detection of Marine Animals in High Resolution Aerial Images

    12/01/2022  ·  Remote Sensing  ·  Paul Berg, Deise Santana Maia, Minh-Tan Pham, Sébastien Lefèvre