no code implementations • 25 Mar 2024 • Nicolas Audinet de Pieuchon, Adel Daoud, Connor Thomas Jerzak, Moa Johansson, Richard Johansson
We investigate the potential of large language models (LLMs) to distill text: to remove the textual traces of an undesired forbidden variable.
no code implementations • 17 Mar 2024 • Daniel Enström, Viktor Kjellberg, Moa Johansson
Transformer language models are neural networks used for a wide variety of tasks concerning natural language, including some that also require logical reasoning.
1 code implementation • 2 Nov 2023 • Lovisa Hagström, Denitsa Saynova, Tobias Norlund, Moa Johansson, Richard Johansson
In this work, we identify potential causes of inconsistency and evaluate the effectiveness of two mitigation strategies: up-scaling and augmenting the LM with a retrieval corpus.
no code implementations • 28 Dec 2022 • Erik Jergéus, Leo Karlsson Oinonen, Emil Carlsson, Moa Johansson
In this paper we take the first steps in studying a new approach to synthesis of efficient communication schemes in multi-agent systems, trained via reinforcement learning.
no code implementations • 7 Sep 2021 • Moa Johansson, Nicholas Smallbone
In this paper, we give a brief overview of a theory exploration system called QuickSpec, which is able to automatically discover interesting conjectures about a given set of functions.
1 code implementation • 23 Apr 2019 • Moa Johansson, Marie Korneliusson, Nickey Lizbat Lawrence
We have conducted a pilot study in the use of machine learning techniques on data from Skisens poles to identify which "gear" a skier is using (double poling or gears 2-4 in skating), based only on the sensor data from the ski poles.
1 code implementation • 1 Aug 2018 • Agrin Hilmkil, Oscar Ivarsson, Moa Johansson, Dan Kuylenstierna, Teun van Erp
Professional sports are developing towards increasingly scientific training methods with increasing amounts of data being collected from laboratory tests, training sessions and competitions.