Passionate about Computer Vision Research.

PhD Student at CTU in Prague (VRG). Instance-level recognition, open-world segmentation and retrieval.

Tilemachos Aravanis

Latest Updates

Best Oral Presentation at Greeks in AI 2026

Retrieve and Segment received the Best Oral Presentation award at the Greeks in AI Symposium 2026 (Athens, 15–17 July 2026). I also volunteered at the event for the second year in a row.

Greeks in AI

CVPR 2026 Highlight

Presented Retrieve and Segment as a Highlight paper at CVPR 2026 (June 2026).

Browse the Project page

Code released

Official implementations of Retrieve and Segment (CVPR 2026) and Only-Style (ICCV-W 2025) are on GitHub.

GitHub

Winter School on Foundation Models (FoMo 2026)

Attended the ELLIS Winter School on Foundation Models in Amsterdam, 24–27 March 2026.

Event details

Best Student Paper Award

Our work Only-Style won the Best Student Paper Award at the Personalization in Generative AI (P13N) Workshop, ICCV 2025.

Read the paper

About Me

I am a second-year PhD student in the Visual Recognition Group (VRG) at CTU in Prague, under the supervision of Giorgos Tolias, working on instance-level recognition, open-world segmentation and retrieval. In a few words, I am trying to create models that recognize (retrieve, classify, detect, segment) particular objects in an open-world environment.

2 Core A* Papers
2 Award-Winning Papers

Selected Publications

Retrieve and Segment thumbnail
CVPR 2026 - Highlight

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

T. Aravanis, V. Stojnić, B. Psomas, N. Komodakis, G. Tolias

Bridging the supervision gap in open-vocabulary segmentation using a few pixel-level annotated examples along with class names.

Attention, Please! thumbnail
ICLR 2026

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

B. Psomas, D. Christopoulos, E. Baltzi, I. Kakogeorgiou, T. Aravanis, N. Komodakis, K. Karantzalos, Y. Avrithis, G. Tolias

A re-examination of attentive probing methods focusing on efficiency-oriented insights.

Only-Style thumbnail
ICCV 2025 Workshops

Only-Style: Stylistic Consistency in Image Generation without Content Leakage

T. Aravanis, P. Filntisis, P. Maragos, G. Retsinas

A method that achieves style-consistent image generation without content leakage.