Doctorant en IA - Trustworthy Multimodal Representation Learning for Dynamic State Modeling and Prediction (H/F)

Description

This PhD position is offered within Efrei Research Lab, as part of the Data & Artificial Intelligence research area.

PhD topic: Trustworthy Multimodal Representation Learning for Dynamic State Modeling and Prediction

Context:

The increasing availability of heterogeneous multimodal data offers new opportunities for artificial intelligence to model complex systems and predict the evolution of their states over time. Such data may originate from multiple sources and exhibit different structures, dimensionalities, sampling rates, and statistical properties.

However, conventional machine learning approaches often rely on observations acquired at a single time point or consider a limited number of modalities. In real-world dynamic systems, observations may instead be collected over time, at irregular intervals, and different modalities may not always be simultaneously available, and some observations may be partially or entirely missing [Huang, 2025] [Lin, 2025]. Moreover, each modality may provide only a partial and complementary view of the underlying state of the observed system.

Recent advances in multimodal learning, temporal modeling, and representation learning provide new opportunities to jointly exploit these heterogeneous observations. Rather than processing each modality or observation independently, these approaches aim to learn unified representations that capture complementary information across modalities as well as relevant dependencies over time.

Recent work on irregular multivariate time series has also highlighted the difficulty of jointly modeling temporal and cross-variable dependencies when observations are unaligned and irregularly sampled [Li, 2025].

In this context, a fundamental challenge is to learn a dynamic latent representation capable of characterizing the current state of a system from heterogeneous and potentially incomplete observations, while preserving the information required to model and predict its future evolution.

The main objective of this thesis is to develop trustworthy multimodal representation learning approaches capable of modeling dynamic states and predicting their future evolution from incomplete temporal observations.

Particular attention will be devoted to four complementary properties of trustworthy prediction: robustness to partial observations and distribution shifts, uncertainty quantification, confidence calibration, and temporal explainability.

The specific tasks of this thesis are:

• State-of-the-art analysis and problem formulation.
• Dynamic multimodal representation learning.
• Trustworthy modeling and prediction.
• Experimental evaluation and validation.

Profile

We are looking for a candidate with a Master’s degree (research-oriented) or an Engineering degree, with a strong background in Machine Learning and Deep Learning.

The ideal candidate should have:

• a strong mathematical background , particularly in linear algebra, probability, statistics, and optimization;
• very good programming skills in Python ;
• the ability to understand, implement, and critically analyze recent machine learning research papers;
• previous research experience, ideally through a Master’s thesis, research internship, or scientific publication.

Experience in at least one of the following areas would be particularly appreciated:

• Representation Learning ;
• Multimodal Learning ;
• Self-Supervised Learning ;
• Time-Series or Sequence Modeling ;
• Probabilistic Machine Learning .

L’Efrei est engagée en faveur de l’égalité des chances et encourage les candidatures de personnes en situation de handicap. Tous nos postes sont ouverts à tous les talents.

Company

Grande École du Numérique créée en 1936, l’Efrei est un acteur indépendant majeur de l’enseignement supérieur et de la transformation numérique. Installée à Paris ainsi qu’à Bordeaux, l’Efrei forme 5 800 étudiants dans son programme Grande École d’ingénieurs et dans ses Programmes Experts du numérique (bachelors, mastères…), et propose également une offre de formation continue.

Rejoindre l’Efrei, c’est bien plus que rejoindre simplement un leader de l’enseignement supérieur de premier plan, c’est vouloir s’engager dans un projet pédagogique et humain centré sur les étudiants, avec l’assurance d’avoir les moyens de ses ambitions tout en vivant dans un cadre professionnel exceptionnel au sein de nos campus.

Leader indépendant reconnu d’intérêt public par l’État (EESPIG), l’Efrei est habilitée par la Commission des titres d’ingénieurs (CTI) et fait partie de la Conférence des Grandes Écoles. Depuis janvier 2022, l’Efrei est établissement composante de Paris Panthéon-Assas Université.