no code implementations • 3 May 2024 • Ashwin Kumar Gururajan, Enrique Lopez-Cuena, Jordi Bayarri-Planas, Adrian Tormos, Daniel Hinjos, Pablo Bernabeu-Perez, Anna Arias-Duart, Pablo Agustin Martin-Torres, Lucia Urcelay-Ganzabal, Marta Gonzalez-Mallo, Sergio Alvarez-Napagao, Eduard Ayguadé-Parra, Ulises Cortés Dario Garcia-Gasulla
In this work, we explore the role of instruct tuning, model merging, alignment, red teaming and advanced inference schemes, as means to improve current open models.
1 code implementation • 8 Nov 2022 • Adrian Tormos, Dario Garcia-Gasulla, Victor Gimenez-Abalos, Sergio Alvarez-Napagao
In deep learning, transfer learning (TL) has become the de facto approach when dealing with image related tasks.
no code implementations • 21 Mar 2022 • Dmitry Gnatyshak, Dario Garcia-Gasulla, Sergio Alvarez-Napagao, Jamie Arjona, Tommaso Venturini
Studying misinformation and how to deal with unhealthy behaviours within online discussions has recently become an important field of research within social studies.
1 code implementation • 22 Apr 2020 • Irene Li, Yixin Li, Tianxiao Li, Sergio Alvarez-Napagao, Dario Garcia-Gasulla, Toyotaro Suzumura
The outbreak of coronavirus disease 2019 (COVID-19) recently has affected human life to a great extent.
no code implementations • 4 Feb 2020 • Mario A. Gutierrez-Mondragon, Dario Garcia-Gasulla, Sergio Alvarez-Napagao, Jaume Brossa-Ordoñez, Rafael Gimenez-Esteban
In this work, we design a methodology to train a Convolutional Neural Network for identifying the level of obstruction in pipes, thus reducing the human effort required on such a frequent and repetitive task.