Eleftherios Tsonis

Hi, I'm Eleftherios, though my friends and most people call me Lefteris! I am a PhD student at École Polytechnique, where I am fortunate to be advised by Prof. Vicky Kalogeiton and Prof. Xi Wang. I am part of the VISTA team at the Computer Science Laboratory (LIX). Prior to this, I was affiliated with the Artificial Intelligence & Learning Systems (AILS) Lab. I earned my Diploma in Electrical & Computer Engineering from the National Technical University of Athens (NTUA).

📧 Email  /  🎓 Scholar  /  📄 LinkedIn  /  🖼️ Gallery  /  💻 Github

profile photo

Research

My research interests lie in multimodal learning, spanning both generative modeling and representation learning across modalities. I am particularly interested in making these systems more expressive, grounded, and effective in real-world contexts.

Image What Images Cannot Say: Language-Guided Olfactory Representation Learning
Eleftherios Tsonis, Xi Wang, Vicky Kalogeiton
ECCV, 2026
[arXiv] [website]
Image One-step Diffusion Models with Bregman Density Ratio Matching
Yuanzhi Zhu, Eleftherios Tsonis, Lucas Degeorge, Vicky Kalogeiton
EurIPS Principles of Generative Modeling (PriGM) Workshop, 2025
[arXiv]
Image Training-Free Synthetic Data Generation with Dual IP-Adapter Guidance
Luc Boudier*, Loris Manganelli*, Eleftherios Tsonis*, Nicolas Dufour, Vicky Kalogeiton
BMVC, 2025
[arXiv] [website] [code]
Image U-Sketch: Bridging the Gap for Efficient and Realistic Sketch-to-Image Synthesis
Ilias Mitsouras, Eleftherios Tsonis, Paraskevi Tzouveli, Athanasios Voulodimos
IEEE Access, 2026
[IEEE] [arXiv]

News

Teaching

École Polytechnique
2025-2026:
  • Multimodal Generative AI (CSC_52002_EP)
  • Deep Learning in Computer Vision (CSC_43M04_EP)
  • Advanced Deep Learning (CSC_52087_EP)

2024-2025:
  • Computer Vision: from Fundamentals to Applications (CSC_52002_EP)
  • Advanced Deep Learning (CSC_52087_EP)
NTUA
2023-2024:
  • Various courses provided by the AILS Lab, on genAI and diffusion models.

Miscellaneous

Template by Jon Barron