Assem Sadek

PhD Candidate

Embodied AI & 3D Vision

Assem Sadek

About Me

I'm a PhD resident in Naver Labs Europe and student at INSA Lyon (Imagine Team - LIRIS). My thesis is co-supervised by Boris Chidlovskii, Christian Wolf and Atilla Baskurt . I'm interested in the field of artificial intelligence and robotics. My work is focused on applying deep learning with 3D Geometry in visual navigation tasks for mobile robots. The main goal is to deploy robust algorithms on robots that can adapt to real world environments, leveraging learning-based techniques and geometry-based techniques.

I received my master degree from the university of Grenoble-Alpes and ENSIMAG in Machine Learning and Data science. I graduated summa cum laude with Bachelor degree in Computer Engineering from Cairo University in Egypt.


Companies I've worked with

  • NAVER LABS Europe

    NAVER LABS Europe

  • Microsoft

    Microsoft

  • Valeo

    Valeo

  • Mentor Graphics

    Mentor Graphics

Research

  • Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction

    Guillaume Bono, Leonid Antsfeld, Assem Sadek, Gianluca Monaci, Christian Wolf

    International Conference on Learning Representations (ICLR 2024)

  • Learning whom to trust in navigation: dynamically switching between classical and neural planning

    Sombit Dey, Assem Sadek, Gianluca Monaci, Boris Chidlovskii, Christian Wolf

    International Conference on Intelligent Robots and Systems (IROS 2023)

  • Multi-Object Navigation in real environments using hybrid policies

    Assem Sadek, Guillaume Bono, Boris Chidlovskii, Atilla Baskurt, Christian Wolf

    International Conference on Robotics and Automation (ICRA-2023)

  • An in-depth experimental study of sensor usage and visual reasoning of robots navigating in real environments

    Assem Sadek, Guillaume Bono, Boris Chidlovskii, Christian Wolf

    International Conference on Robotics and Automation (ICRA-2022)

  • Universal Domain Adaptation in Ordinal Regression

    Boris Chidlovskii, Assem Sadek, Christian Wolf

    Arxiv

  • Adversarial Transfer of Pose Estimation Regression

    Boris Chidlovskii, Assem Sadek

    European Conference on Computer Vision (ECCV-2020), TASK-CV Workshop

  • Self-Supervised Attention Learning for Depth and Ego-motion Estimation

    Assem Sadek, Boris Chidlovskii

    International Conference on Intelligent Robots and Systems (IROS-2020)