Antonios Vozikis

Hi and welcome!

My primary research interests lie in Generative AI, Geometric Deep Learning and Foundation Models. I hold a Master’s in Artificial Intelligence from Vrije Universiteit (VU), in collaboration with Universiteit van Amsterdam (UvA) (Grade 8.5/10). My thesis research focused on Generative AI Architectures for Structured Graphs, received a 9/10.

I am a graduate in Electrical and Computer Engineering with a lifelong passion for Mathematics. From a young age, I found joy in solving mathematical problems, which driven by curiosity,led me into the field of AI.

When I’m not immersed in my research, I enjoy reading a wide range of books, indulging in a good cup of coffee, and taking long walks in nature. These activities not only provide relaxation but also inspire new ideas and perspectives.

news

Oct 30, 2025	I had the plesure of presenting the work on Generative AI for Graphs on the ELLIS Amsterdam Research Retreat. This was a wonderful experience, and I am very happy to have been able to share the work with the community.
Oct 16, 2025	Check out this new article i co-authored in AI for Food Allergies as part of the HuggingFace Science collaboration team. It’s a great example of how AI can be used to improve the quality of life for people with food allergies.
Sep 01, 2025	I’m excited to share that I’ll be a scientific supervisor in Embodied AI, for the research projects of the master students for the course of Evolutionary Computing at VU Amsterdam!
Apr 01, 2025	I’m excited to share that I’ll be a teaching assistant for the master course Natural Language Processing at VU Amsterdam!
Jan 01, 2025	I’m excited to share that I’ll be a teaching assistant for the master course Machine Learning for Graphs at VU Amsterdam!
Nov 01, 2024	I’m excited to share that I’ll be a teaching assistant for the master course Deep Learning at VU Amsterdam!
Oct 01, 2024	Excited to have completed my research project at CWI, where I designed the entire pipeline, explored cutting-edge techniques, combining deep learning models with SHAP values and large language models to transform black-box predictions into actionable maintenance insights. It feels incredibly rewarding to see my hard work come together, especially in such an innovative application of AI!Check my work under the supervision of Eric Pauwels here CWI Research Project
Jul 22, 2024	Blogpost accepted in ICML 2024. Find more details here: GRaM Workshop

selected publications

When Simplicity Wins: Efficient Knowledge Graph Generation with Sequential Decoders

Thiviyan Thanapalasingam^*, Antonios Vozikis^*, Peter Bloem , and 1 more author

Sep 2025

Bib HTML

@article{SequentialKGGeneration,
  title = {When Simplicity Wins: Efficient Knowledge Graph Generation with Sequential Decoders},
  author = {Thanapalasingam, Thiviyan and Vozikis, Antonios and Bloem, Peter and Groth, Paul},
  year = {2025},
  month = sep,
  url = {https://openreview.net/forum?id=e1Lmkw35DG},
}

Morpheus: Benchmarking Physical Reasoning of Video Generative Models with Real Physical Experiments

Chenyu Zhang, Daniil Cherniavskii, Andrii Zadaianchuk , and 7 more authors

Apr 2025

Bib HTML

@article{MorpheusBenchmark,
  title = {Morpheus: Benchmarking Physical Reasoning of Video Generative Models with Real Physical Experiments},
  author = {Zhang, Chenyu and Cherniavskii, Daniil and Zadaianchuk, Andrii and Tragoudaras, Antonios and Vozikis, Antonios and Nijdam, Thijmen and Prinzhorn, Derck W. E. and Bodracska, Mark and Sebe, Nicu and Gavves, Efstratios},
  year = {2025},
  month = apr,
  url = {https://arxiv.org/abs/2504.02918},
}

ICML

Equivariant Diffusion for Molecule Generation in 3D using Consistency Models

M. Sedlacek^*, A. Vozikis^*, P. Bartak , and 2 more authors

ICML, GRaM Workshop, Jul 2024

Bib HTML

@article{EquivariantGeneration,
  title = {Equivariant Diffusion for Molecule Generation in 3D using Consistency Models},
  author = {Sedlacek, M. and Vozikis, A. and Bartak, P. and Cadigan, L. and Guo, M.},
  journal = {ICML, GRaM Workshop},
  year = {2024},
  month = jul,
  url = {https://gram-blogposts.github.io/blog/2024/equivariant_diffusion},
}

latest posts

Jun 30, 2024	Equivariant Diffusion for Molecule Generation in 3D using Consistency Models