Sort by
Refine Your Search
-
Listed
-
Employer
- CNRS
- Inria, the French national research institute for the digital sciences
- IMT Atlantique
- Télécom Paris
- Université Grenoble Alpes
- Université Savoie Mont Blanc
- Université de Bordeaux / University of Bordeaux
- Avignon Université
- Fondation nationale des Sciences Politiques
- IMT - Institut Mines-Télécom
- IMT MINES ALES
- IMT Nord Europe
- INSERM U1028
- INSTITUT MAX VON LAUE - PAUL LANGEVIN
- Inserm PACA Corsica
- Institut Curie - Research Center
- UNIVERSITE ANGERS
- UNIVERSITE D'ORLEANS
- Universite de Montpellier
- Université côte d'azur
- 10 more »
- « less
-
Field
-
quantitative and machine learning approaches ● Developing predictive models linking nuclear features to future cell fate ● Interacting with collaborators in imaging, computational biology, and developmental
-
Description Within the ANR HEBBIAN contract, the objective is to adapt bio-inspired Hebbian learning models recently proposed by one of the partners of this ANR (Frédéric Lavigne) in order to account for data
-
intelligence, and multimodal learning. The main objective of this position is to develop novel generative AI methods for computer vision applications, with a particular focus on Diffusion Models and Vision
-
the research activities entrusted to the officer take place: This ANR project lies at the interface between statistical learning (mainly deep learning) and combinatorial optimization (mainly stochastic and
-
). Deep learning has been used to perform this mapping from UAV (Batista et al., 2025; Chudasama et al., 2024; Lambert et al., 2025) or satellite imagery (Mattéo et al., 2021), at both very high resolution
-
structure calculations, vibronic property simulations, and analyzing surface adsorption phenomena. Knowledge of machine learning potentials (e.g., GAP, ACE) or reactive force fields is a plus, as fallback
-
biology skills Experience with single-cell RNA-seq analysis Experience with machine learning based methods Have evidence of scientific accomplishment via peer-reviewed publications Understanding of cancer
-
for the analysis of hyperspectral imaging data applied to pictorial layers, based on coupling physical radiative transfer models (two-flux and four-flux approaches) with machine learning methods. The researcher will
-
at the metropolitan scale • Integration of AI-based learning capabilities to refine all types of models studied • Consideration of environmental aspects in the comparative evaluation (positive impact and modal switch
-
FieldMathematicsYears of Research ExperienceNone Additional Information Eligibility criteria PhD in computer science, deep learning, or data science. Experience with multimodal models for biological data. Website