Mes recherches portent sur la théorie des probabilités. Plus précisément, voici les sujets sur lesquels j'ai publié des articles :

• l'apprentissage statistique, les réseaux neuronaux, les modèles de mémoire associative, le modèle de Hopfield.
• l'imagerie médicale.
• les sciences actuarielles.
• la physique statistique.
• les algorithmes stochastiques, les méthodes de Monte Carlo.
• le traitement automatique du langage.
• la théorie de la communication multi-utilisateurs.
• les marches aléatoires.

Voici la liste complète de mes publications (l'autre 'onglet "Publications" est une extraction automatique de HAL) :

Prépublications :

• A. Charpentier, L. Kouakou, M. Löwe, Ph. Ratz, F. Vermet, Collaborative Insurance Sustainability and Network Structure. (2021) (arXiv:2107.02764)
   
• M. Moriah, F. Vermet, P. Ailliot, P. Naveau, J. Legrand, Contributions of geolocated weather and building related data for insurance assessment of flood risks. (2026) (arXiv:2603.02418)
   
• M. Löwe, F. Vermet, On associative neural networks for sparse patterns with huge capacities. (2026) (arXiv:2603.26217)

Articles de recherche publiés :

• B. Uthayasooriyar, A. Ly, F. Vermet, C. Corro, DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), 3897-3907 (2026) (pdf)
   
• C. Vazia, T. Dassow, A. Bousse, J. Froment, B. Vedel, F. Vermet, A. Perelli, J.-P. Tasu, D. Visvikis, Material Decomposition in Photon-Counting Computed Tomography With Diffusion Models: Comparative Study and Hybridization With Variational Regularizers. IEEE Transactions on Radiation and Plasma Medical Sciences( 2026) (arXiv:2503.15383) (DOI: 10.1109/TRPMS.2026.3651354)
   
• B. Uthayasooriyar, A. Ly, F. Vermet, C. Corro, Training LayoutLM from Scratch for Efficient Named-Entity Recognition in the Insurance Domain, Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal), janvier 2025, Abu Dabi, ae, ⟨hal-04877824⟩
   
• N. El Bekri, L. Drumetz, F. Vermet, FlowKac: An Efficient Neural Fokker-Planck solver using Temporal Normalizing flows and the Feynman Kac-Formula.  Transactions on Machine Learning Research (2025) (https://openreview.net/pdf?id=paeyQFa5or)
   
• C. Vazia, A. Bousse, B. Vedel, F. Vermet, Z. Wang, Th.Dassow, J.-P. Tasu, D. Visvikis, J. Froment. Spectral CT Two-step and One-step Material Decomposition using Diffusion Posterior Sampling. 2024 32nd European Signal Processing Conference (EUSIPCO), Lyon, France, 2024, pp. 1506-1510 (https://ieeexplore.ieee.org/document/10715152) (arXiv:2403.10183)
   
• R. Lafargue, L. A. Smith, F. Vermet, M. Löwe, I. Reid, J. Valmadre, V. Gripon. Oops, I Sampled it Again: Reinterpreting Confidence Intervals in Few-Shot Learning. Transactions on Machine Learning Research (2024) (https://openreview.net/pdf?id=JxxkKt9yrx)
   
• C. Vazia, A. Bousse, B. Vedel, F. Vermet, Z. Wang, Th.Dassow, J.-P. Tasu, D. Visvikis, J. Froment. Diffusion Posterior Sampling for Synergistic Reconstruction in Spectral Computed Tomography, 2024 IEEE International Symposium on Biomedical Imaging (ISBI), Athens, Greece, 2024, pp. 1-5, (doi: 10.1109/ISBI56570.2024.10635735). (arXiv:2403.06308)
   
• P. Soto Vega, V. Bourbonne, W. Marchadour, G. Andrade-Miranda, F. Lucia, M. Rehn, U. Schick, D. Visvikis, F. Vermet, M. Hatt, Prediction of Acute Pulmonary Toxicity Events with 3D Convolutional Neural Networks from Radiotherapy Dose Maps. XXth International Conference on the use of Computers in Radiation therapy, Lyon (2024) (hal-04655207)
   
• A. Charpentier, M. Moriah, F. Vermet, Measuring and Mitigating Biases in Motor Insurance Pricing. Eur. Actuar. J.,14, 833-869 (2024) (arXiv:2311.11900) (doi : 10.1007/s13385-024-00390-8)
   
• N. El Bekri, L. Drumetz, F. Vermet, Time Changed Normalizing Flows for Accurate SDE Modeling, ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, Republic of, 6395-6399 (2024) (doi: 10.1109/ICASSP48485.2024.10446131)
   
• Z. Wang, A. Bousse, F. Vermet, J. Froment, B. Vedel, A. Perelli,  J.-P. Tasu, D. Visvikis. Uconnect: Synergistic Spectral CT Reconstruction with U-Nets Connecting the Energy bins.  IEEE Transactions on Radiation and Plasma Medical Sciences, 8(2), 222-233 (2024) (arXiv:2311.00666)
   
• L. Drumetz, L., A. Reiffers-Masson, N. El Bekri, F. Vermet, Geometry-Preserving Lie Group Integrators for Differential Equations on the Manifold of Symmetric Positive Definite Matrices. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2023. Lecture Notes in Computer Science, vol 14072. Springer, Cham. (https://doi.org/10.1007/978-3-031-38299-4_45) (arxiv:2210.08842)
   
• D. Delcaillau, A. Ly, A. Papp, F. Vermet, Model Transparency and Interpretability : Survey and Application to the Insurance Industry.  Eur. Actuar. J., 12, 443-484 (2022) (https://doi.org/10.1007/s13385-022-00328-y) (arXiv:2209.00562) 
   
• Z. Wang, A. Bousse, N.J. Pinton, J. Froment, F. Vermet, B. Vedel, J.-P. Tasu, D. Visvikis, Synergistic Multi-Energy CT Reconstruction with a Deep Penalty “Connecting the Energies”, 2022 IEEE Nuclear Science Symposium (NSS), Medical Imaging Conference (MIC) and Room Temperature Semiconductor Detector (RTSD) Conference, IEEE, novembre 2022, Milan, IT, ⟨hal-03955092⟩
   
• W. Marchadour, B. Badic, J. Maison, M. Hatt, F. Vermet, Comparison of interpretability methods in the context of deep neural networks for radiomics application. Journal of Nuclear Medicine Aug 2022, 63 (supplement 2) 3216 (https://jnm.snmjournals.org/content/63/supplement_2/3216)
   
• P. L. Brocki, W. Marchadour, J. Maison, B. Badic, P. Papadimitroulas, M. Hatt, F. Vermet, N. Ch. Chung, Evaluation of Importance Estimators in Deep Learning Classifiers for Computed Tomography. In: Calvaresi, D., Najjar, A., Winikoff, M., Främling, K. (eds) Explainable and Transparent AI and Multi-Agent Systems. EXTRAAMAS 2022. Lecture Notes in Computer Science(), vol 13283. Springer, Cham (https://doi.org/10.1007/978-3-031-15565-9_1) (arXiv:2209.15398) 
   
• Th. Giraudon, V. Gripon, M. Löwe, F. Vermet, Towards an Intrinsic Definition of Robustness for a Classifier. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4015-4019 (2021) (doi: 10.1109/ICASSP39728.2021.9414573) (arXiv:2006.05095) (https://2021.ieeeicassp.org/)
   
• P. Papadimitroulas, L. Brocki, N. C. Chung, W. Marchadour, F. Vermet, L. Gaubert, V. Eleftheriadis, D. Plachouris, D. Visvikis, G. C. Kagadis, M. Hatt, Artificial Intelligence: Deep learning in oncological radiomics and challenges of interpretability and data harmonization. Physica Medica, 83, 108-121 (2021) (https://doi.org/10.1016/j.ejmp.2021.03.009) 
   
• V. Gripon, M. Löwe, F. Vermet, Some Remarks on Replicated Simulated Annealing.   J. Stat. Phys. 182, 51 (2021) (https://doi.org/10.1007/s10955-021-02727-z) (arXiv:2009.14702)
   
• M. Löwe, K. Schubert, F. Vermet, Multi-group Binary Choice with Social Interaction and a Random Communication Structure - a Random Graph Approach.   Physica A: Stat. Mech. Appl. 556, 124735 (2020) (arXiv:1904.11890)
   
• V. Gripon, G. B. Hacene, M. Löwe, F. Vermet, Improving Accuracy of Nonparametric Transfer Learning via Vector Segmentation.  IEEE ICASSP 2018, 2966-2970 (2018) (arXiv:1710.08637)
   
• V. Gripon, M. Löwe, F. Vermet, Associative Memories to Accelerate Approximate Nearest Neighbor Search.  Appl. Sci. 8(9), 1676 (2018) (Open Access)
   
• M. Demircigil, J. Heusel, M. Löwe, S. Upgang, F. Vermet, On a model of associative memory with huge storage capacity.  J. Stat. Phys. 168 (2), 288-299 (2017) (arXiv:1702.01929)
   
• V. Gripon, J. Heusel, M. Löwe, F. Vermet, A comparative study of sparse associative memories. J. Stat. Phys. 164 (1), 105-129  (2016) (arXiv:1512.08892)
   
• J. Heusel, M. Löwe, F. Vermet, On the capacity of a new model of associative memory based on neural cliques. Stat. & Prob. Lett., 106, 256-261 (2015) (arXiv:1411.1224)
   
• M. Löwe, F. Vermet, Capacity of an associative memory model on random graph architectures. Bernoulli 21 (3), 1884-1910 (2015)  (arXiv:1303.4542)
   
• M. Ebbers, H. Knöpfel, M. Löwe,  F. Vermet,  Mixing times for the Swapping Algorithm on the Blume-Emery-Griffiths Model. Random Structures & Algorithms 45 (1), 38-77 (2014) (arXiv:1206.4162)
   
• C. Wright, R. B. Scott, D. Furnival, P. Ailliot, F. Vermet, Global Observations of Ocean-Bottom Subinertial Current Dissipation. Journal of Physical Oceanography 43 (2), 402-417 (2013)
   
• M. Löwe,  F. Vermet,  The Hopfield model on a sparse Erdö-Renyi graph.  J. Stat. Phys. 143, 205-214 (2011) 
   
• M. Löwe, F. Vermet, The swapping algorithm for the Hopfield model with two patterns. Stochastic Process. Appl. 119 (10), 3471-3493 (2009)
   
• M. Löwe, F. Vermet, Capacity bounds for the CDMA system and a neural network : a moderate deviations approach.  ESAIM Probab. Stat. 13, 343- 362 (2009)
   
• M. Löwe, F. Vermet, The Capacity of q-state Potts neural networks with Parallel Retrieval Dynamics.  Stat. & Prob. Lett. 77, 1505-1514 (2007)
   
• R. van der Hofstad, M. Löwe, F. Vermet,  The effect of system load on the existence of bit-errors in CDMA with and without parallel interference cancelation.  IEEE Transactions on Information Theory 52, 4733-4741 (2006)
   
• M. Löwe, F. Vermet, The storage capacity of the Hopfield model and moderate deviations. Stat. & Prob. Lett., 75, 237-248 (2005)
   
• M. Löwe, F. Vermet, The storage capacity of the Blume-Emery-Griffiths neural network. J. Phys. A : Math. Gen., 38 (16), 3483-3503 (2005)
   
• F. Vermet, Phase transition and law of large numbers for a non-symmetric one-dimensional random walk with self-interactions. J. Appl. Prob., 35, 55-63 (1998)
   
• F. Vermet, Transition de phase et vitesse de fuite pour une mesure discrète de Edwards non symétrique sur Z. (French) (Phase transition and escape speed for a nonsymmetric discrete Edwards measure on Z) C. R. Acad. Sci. Paris Sér. I Math. 322 (1996), no. 6, 567-570 (1996)
   
• F. Vermet, Discrétisation d'une équation différentielle stochastique dont les coefficients ne dépendent pas du temps et calcul approché d'espérances de fonctionnelles de la solution. (French) (Discretization of a stochastic differential equation whose coefficients are not time-dependent, and rough estimate of the expectations of functionals of the solution) Fascicule de probabilités, 65 pp., Publ. Inst. Rech. Math. Rennes, Univ. Rennes I, Rennes (1992) (pdf)
   
• F. Vermet, Convergence de la variance de l'énergie libre pour le modèle de Hopfield. (French) |LS|Convergence of the variance of the free energy in the Hopfield model|RS| C. R. Acad. Sci. Paris Sér. I Math. 315 (1992), no. 9, 1001-1004 (1992)

Habilitation à Diriger des Recherches : 

• Etude probabiliste de modèles neuronaux de mémoire associative et d'algorithmes utilisés en physique statistique et data science.  (pdf)
  Université de Bretagne Occidentale, Brest,  France (2019)

Thèse de Doctorat :  

• Etude asymptotique d'un réseau neuronal : le modèe de mémoire associative de Hopfield. Université de Rennes 1,  France (1994) http://tel.archives-ouvertes.fr/tel-00598243/fr/