no code implementations • 6 Feb 2024 • Spyridon Mouselinos, Henryk Michalewski, Mateusz Malinowski
Large Language Models (LLMs) demonstrate ever-increasing abilities in mathematical and algorithmic tasks, yet their geometric reasoning skills are underexplored.
no code implementations • 31 Oct 2022 • Spyridon Mouselinos, Mateusz Malinowski, Henryk Michalewski
This work shows that current code generation systems exhibit undesired biases inherited from their large language model backbones, which can reduce the quality of the generated code under specific circumstances.
no code implementations • 24 Feb 2022 • Spyridon Mouselinos, Henryk Michalewski, Mateusz Malinowski
Visual question answering provides a convenient framework for testing the model's abilities by interrogating the model through questions about the scene.
no code implementations • ICLR 2022 • Spyridon Mouselinos, Henryk Michalewski, Mateusz Malinowski
To answer such a question, we extend the visual question answering framework and propose the following behavioral test in the form of a two-player game.
no code implementations • 10 Feb 2021 • Spyridon Mouselinos, Kyriakos Polymenakos, Antonis Nikitakis, Konstantinos Kyriakopoulos
The problem of missing data, usually absent incurated and competition-standard datasets, is an unfortunate reality for most machine learning models used in industry applications.