Zobrazeno 1 - 10
of 449 608
pro vyhledávání: '"Adriana, A."'
We examine the problem of assigning teachers to public schools over time when teachers have tenured positions and can work simultaneously in multiple schools. To do this, we investigate a dynamic many-to-many school choice problem where public school
Externí odkaz:
http://arxiv.org/abs/2411.07851
Recent advances in generative artificial intelligence (AI) have shown promise in accurately grading open-ended student responses. However, few prior works have explored grading handwritten responses due to a lack of data and the challenge of combinin
Externí odkaz:
http://arxiv.org/abs/2411.05231
Autor:
Berrada, Tariq, Astolfi, Pietro, Verbeek, Jakob, Hall, Melissa, Havasi, Marton, Drozdzal, Michal, Benchetrit, Yohann, Romero-Soriano, Adriana, Alahari, Karteek
Latent diffusion models (LDMs) power state-of-the-art high-resolution generative image models. LDMs learn the data distribution in the latent space of an autoencoder (AE) and produce images by mapping the generated latents into RGB image space using
Externí odkaz:
http://arxiv.org/abs/2411.04873
Traffic flow forecasting is a crucial task in intelligent transport systems. Deep learning offers an effective solution, capturing complex patterns in time-series traffic flow data to enable the accurate prediction. However, deep learning models are
Externí odkaz:
http://arxiv.org/abs/2411.03588
Autor:
Ifriqi, Tariq Berrada, Astolfi, Pietro, Hall, Melissa, Askari-Hemmat, Reyhane, Benchetrit, Yohann, Havasi, Marton, Muckley, Matthew, Alahari, Karteek, Romero-Soriano, Adriana, Verbeek, Jakob, Drozdzal, Michal
Large-scale training of latent diffusion models (LDMs) has enabled unprecedented quality in image generation. However, the key components of the best performing LDM training recipes are oftentimes not available to the research community, preventing a
Externí odkaz:
http://arxiv.org/abs/2411.03177
The 2D toric code is a prototypical example that exhibits non-trivial topological properties and a ground state possessing a non-trivial topological order. Until now, all the cases studied in the literature have been in the stable equilibrium regime,
Externí odkaz:
http://arxiv.org/abs/2410.24033
Recent advances in parameter-efficient fine-tuning methods, such as Low Rank Adaptation (LoRA), have gained significant attention for their ability to efficiently adapt large foundational models to various downstream tasks. These methods are apprecia
Externí odkaz:
http://arxiv.org/abs/2410.17358
Autor:
De-Rosende-Celeiro, Iván, Francisco-Gilmartín, Virginia, Bautista-Blasco, Susana, Ávila-Álvarez, Adriana
Publikováno v:
DIGITAL HEALTH. 2024;10
Objective: The objectives encompassed (1) the creation of Recuerdame, a digital app specifically designed for occupational therapists, aiming to support these professionals in the processes of planning, organizing, developing, and documenting reminis
Externí odkaz:
http://arxiv.org/abs/2410.13556
This paper investigates the under-explored area of low-rank weight training for large-scale Conformer-based speech recognition models from scratch. Our study demonstrates the viability of this training paradigm for such models, yielding several notab
Externí odkaz:
http://arxiv.org/abs/2410.07771
Autor:
Răgman, Teodora, Stan, Adriana
This paper focuses on adapting the functionalities of the FastPitch model to the Romanian language; extending the set of speakers from one to eighteen; synthesising speech using an anonymous identity; and replicating the identities of new, unseen spe
Externí odkaz:
http://arxiv.org/abs/2410.06787