Recherche

D’où viendront les trois prochaines années de ce travail.

Le travail derrière les systèmes : mémoires, projets, méthodes employées et questions auxquelles ils devaient répondre.

• Prédiction de l'expression génique (biologie moléculaire) à partir d'images de pathologie numérique

  Gene-expression assays are slow, expensive and logistically painful. Whole-slide pathology images are fast and cheap. This thesis asks whether the second can stand in for the first — recovering molecular-biology signal directly from gigapixel pathology images, under a hard constraint on compute and latency. The approach combines graph neural networks, vision foundation models, large-language-model techniques adapted for this task, and statistical/probabilistic methods.

• Simulation de la cognition visuelle humaine et distinction entre perception réelle et hallucination

  A year-long study using generative models — autoencoders and GANs — to model how the human brain constructs visual understanding, and to distinguish genuine perception from hallucination.