Random Name


PhD student in Computer Science

Specialized in interpretability

Work Experience Social Publication

About Me

I am a sociable, meticulous student with excellent ability to multi-task and demonstrate great resistance to stress. I have skills in the fields of finance, public relations and computer science.
I am 23 years old and beginning my first year of PhD in computer sciences at Rennes 1 university. My thesis is about Automatic Construction of Explanations for AI Models. My supervisors are Christine Largouët and Luis Galarraga. The purposes is to extend actual interpretable methods for machine learning methods in order to create a novel tool that explains the inner mechanisms of the model.
Due to recent advances in AI and in particular in deep learning, models are becoming more and more difficult to trust since their success is often due to their high complexity. Relying on the answers of a black box can be an issue for technical, ethical and legal reasons.

Work experience


  • PhD student supervised by Christine largouët and Luis Galarraga in interpretability
  • The recently approved GDPR contemplates the right of individuals to contest decisions made on their personal data. That encompasses decisions made by algorithms. To select the most suitable explanation for a use case taking into account criteria such as fidelity, complexity, scope, semantics, and the target user. Such a task is far from trivial because it requires a knowledge of the guarantees of the different explanation methods, as well as an analysis of the context in which the explanation will be delivered.
    This task is time-consuming and unfeasible for non-technical users. We argue, however, that it can be automated.


  • 6 months internship in Lacodam team supervised by Luis Galarraga and Christine largouët
  • In order to complete my research master's degree, I did an internship in a research laboratory. This internship is taking part in the FaBlE project that leads to my PhD thesis. The purposes of this internship is to discover "when are anchors based explanation not a good idea ?" Anchors is a local interpretability method based on decision rules introduced by Marco Tulio Ribeiro, the author of Lime.
    This internship ended with the publication of our work in the international conference CIKM. Throughout this internship, I studied discretization method on Anchors and improve it with MDLP. While for textual data I expanded the interpretable research space by adding pertinent negatives.


  • In charge of communication for the association of resident of Sherbrooke University. Agrus
  • I was in charge of the communication of an association with more than 500 adherent members. I create events, and share them on social networks. I took part of the organization for some events like the visit of a sugar shack or the winter carnaval in Québec.


  • 4 months internship in Lacodam team supervised by Luis Galarraga
  • At the end of my licence, I did an internship in a lab research team. This internship ended with the writing of an article concerning the mining of referring expressions published in the international conference EDBT 2020.. During this internship I coded a programm called REMI supervised by Luis Galarraga and Jean-Louis Dessalles.
    A referring expression(RE) is a description that identifies a set of instances unambiguously. Mining REs from data finds applications in natural language generation, algorithmic journalism, and data maintenance. Since there may exist multiple REs for a given set of entities, it is common to focus on the most intuitive ones, i.e., the most concise and informative. In this paper we presented REMI, a system that can mine intuitive REs on large RDF knowledge bases.
  • Vacataire Champs libres
  • During my two years student job in this library, I was doing public service, organize the books and the reception of the users.


  • Luis Galarrage, Julien Delaunay, Jean-Louis Dessalles. REMI: Mining Intuitive Referring Expressions. International Conference on Extending Database Technology (EDBT/ICDT), Copenhagen. [Technical report] [Full text] [Presentation]

  • Julien Delaunay, Luis Galarraga, Christine largouët Improving Anchor-based Explanations. Poster at the Conference on Information and Knowledge Management (CIKM.), Galway. [Preprint]
  • julien.delaunay@irisa.fr

    Rennes, France



    PhD student in computer science,
    University of Rennes 1, France, 2020-2023

    Research master's degree in computer science,
    University of Rennes 1, France, 2019-2020

    Master's degree in computer science,
    University of Sherbrooke, Canada, 2018-2019

    University degree MIAGE informatics methods applied to business management,
    University of Rennes 1, France, 2015-2018

    Scientific and european baccalaureate,
    High School St Martin, Rennes, France, 2012-2015

    Technical skills

  • Python
  • Java
  • Latex
  • Html, css
  • javascript, php
  • Android
  • SQL
  • Languages

  • French
  • Native speaker
  • English
  • Professional level
  • Spanish
  • Basic skills
  • Chinese
  • Beginner level