Konstantinos Pitas
Machine Learning Research Scientist @ Cognex Corporation
kostasp210♪gmail.com
I am broadly interested in attention-based models and have also researched various topics in ML Safety such as uncertainty estimation for closed-source models and deep ensembles.
Previously, I worked as a postdoctoral researcher at Inria Grenoble Rhône-Alpes 🇫🇷, where I collaborated with Julyan Arbel and Emtiyaz Khan (🇯🇵). In 2020, I completed my Ph.D. at EPFL🇨🇭, which I obtained under the supervision of professor Pierre Vandergheynst. I completed my MSc. and BSc. in Electrical and Computer Engineering at the Aristotle University of Thessaloniki 🇬🇷.
I’m very passionate about transparent governance and enjoy analysing various topics on political polling and psephology on kassiope.org (in Greek).
News
| Mar 22, 2025 |
U-ensembles: Improved diversity in the small data regime using unlabeled data accepted at AABI 2025 (co-located with ICLR 2025)  
|
|---|---|
| May 22, 2024 |
Just rephrase it! Uncertainty estimation in closed-source language models via multiple rephrased queries accepted at SoLaR @ Neurips 2024
|
| Apr 1, 2024 |
I joined Cognex as a Machine Learning Research Scientist!
|
| Oct 4, 2023 | Something for (almost) nothing: Improving deep ensemble calibration using unlabeled data, new Arxiv preprint |
| Sep 11, 2023 |
The fine print on tempered posteriors, accepted at ACML2023!
|