Bill Psomas

Building G, Room 10

Karlovo náměstí 13

120 00 Nové Město, Prague

I am a postdoctoral researcher in Computer Vision and Machine Learning working at the Visual Recognition Group of Czech Technical University in Prague. I was recently awarded the MSCA Postdoctoral Fellowship 2024 for my project Retrieval-Augmented VIsion-Language Models for Open-vocabulary LocalizatIon (RAVIOLI).

I received my Ph.D. in September 2024 from the National Technical University of Athens (NTUA), where I defended my dissertation, Learning Visual and Multimodal Representations, under the supervision of Konstantinos Karantzalos and Yannis Avrithis.

I have gained research experience through internships at leading institutes such as Inria Rennes, Institute of Advanced Research in Artificial Intelligence (IARAI), and Athena Research Center. I have published 7 papers in A* venues including CVPR, ICCV, ECCV, ICLR, and NeurIPS, in addition to journal and workshop publications. Beyond research, I contribute to the academic community through reviewing, teaching, workshop organization, and student supervision.

news

Feb 20, 2026	Accepted to CVPR 2026 — Retrieve and Segment 🎉
Jan 25, 2026	Accepted to ICLR 2026 — Revisiting Attentive Probing Through the Lens of Efficiency 🎉
Sep 18, 2025	Accepted to NeurIPS 2025 — Instance-Level Composed Image Retrieval 🎉
Feb 10, 2025	Awarded MSCA Postdoctoral Fellowship 🎉
Sep 10, 2024	PhD Defense Complete 🎉

selected publications

CVPR

Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?

Tilemachos Aravanis, Vladan Stojnić, Bill Psomas, and 2 more authors

In Conference on Computer Vision and Pattern Recognition, 2026

arXiv Bib Code

@inproceedings{aravanis2026retrieve,
  title = {Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?},
  author = {Aravanis, Tilemachos and Stojni{\'c}, Vladan and Psomas, Bill and Komodakis, Nikos and Tolias, Giorgos},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year = {2026},
}

ICLR

Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency

Bill Psomas, Dionysis Christopoulos, Eirini Baltzi, and 6 more authors

In International Conference on Learning Representations, 2026

arXiv Bib Code

@inproceedings{psomas2026attention,
  title = {Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency},
  author = {Psomas, Bill and Christopoulos, Dionysis and Baltzi, Eirini and Kakogeorgiou, Ioannis and Aravanis, Tilemachos and Komodakis, Nikos and Karantzalos, Konstantinos and Avrithis, Yannis and Tolias, Giorgos},
  booktitle = {International Conference on Learning Representations},
  year = {2026},
}

NeurIPS

Instance-Level Composed Image Retrieval

Bill Psomas, George Retsinas, Nikos Efthymiadis, and 5 more authors

In Advances in Neural Information Processing Systems, 2025

arXiv Bib Code

@inproceedings{psomas2025instancelevel,
  title = {Instance-Level Composed Image Retrieval},
  author = {Psomas, Bill and Retsinas, George and Efthymiadis, Nikos and Filntisis, Panagiotis and Avrithis, Yannis and Maragos, Petros and Chum, Ondrej and Tolias, Giorgos},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2025},
}

ICCV

Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?

Bill Psomas, Ioannis Kakogeorgiou, Konstantinos Karantzalos, and 1 more author

In International Conference on Computer Vision, 2023

arXiv Bib Code

@inproceedings{psomas2023keep,
  author = {Psomas, Bill and Kakogeorgiou, Ioannis and Karantzalos, Konstantinos and Avrithis, Yannis},
  title = {Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?},
  booktitle = {International Conference on Computer Vision},
  year = {2023},
}

ICLR

It Takes Two to Tango: Mixup for Deep Metric Learning

Shashanka Venkataramanan, Bill Psomas, Ewa Kijak, and 3 more authors

In International Conference on Learning Representations, 2022

arXiv Bib Code

@inproceedings{venkataramanan2022takes,
  title = {It Takes Two to Tango: Mixup for Deep Metric Learning},
  author = {Venkataramanan, Shashanka and Psomas, Bill and Kijak, Ewa and Amsaleg, Laurent and Karantzalos, Konstantinos and Avrithis, Yannis},
  booktitle = {International Conference on Learning Representations},
  year = {2022},
}

ECCV

What to Hide from Your Students: Attention-Guided Masked Image Modeling

Ioannis Kakogeorgiou, Spyros Gidaris, Bill Psomas, and 4 more authors

In European Conference on Computer Vision, 2022

arXiv Bib Code

@inproceedings{kakogeorgiou2022hide,
  author = {Kakogeorgiou, Ioannis and Gidaris, Spyros and Psomas, Bill and Avrithis, Yannis and Bursuc, Andrei and Karantzalos, Konstantinos and Komodakis, Nikos},
  title = {What to Hide from Your Students: Attention-Guided Masked Image Modeling},
  booktitle = {European Conference on Computer Vision},
  year = {2022},
}