Zobrazeno 1 - 10
of 3 089
pro vyhledávání: '"A. Sperduti"'
Graph generative models can be classified into two prominent families: one-shot models, which generate a graph in one go, and sequential models, which generate a graph by successive additions of nodes and edges. Ideally, between these two extreme mod
Externí odkaz:
http://arxiv.org/abs/2408.13194
Large Language Models (LLMs) achieve impressive performance in a wide range of tasks, even if they are often trained with the only objective of chatting fluently with users. Among other skills, LLMs show emergent abilities in mathematical reasoning b
Externí odkaz:
http://arxiv.org/abs/2406.06588
Modern neural network architectures still struggle to learn algorithmic procedures that require to systematically apply compositional rules to solve out-of-distribution problem instances. In this work, we focus on formula simplification problems, a c
Externí odkaz:
http://arxiv.org/abs/2402.17407
Large Language Models (LLMs) have revolutionized the field of Natural Language Processing thanks to their ability to reuse knowledge acquired on massive text corpora on a wide variety of downstream tasks, with minimal (if any) tuning steps. At the sa
Externí odkaz:
http://arxiv.org/abs/2402.17396
Autor:
Susanna Sawyer, Pere Gelabert, Benjamin Yakir, Alejandro Llanos-Lizcano, Alessandra Sperduti, Luca Bondioli, Olivia Cheronet, Christine Neugebauer-Maresch, Maria Teschler-Nicola, Mario Novak, Ildikó Pap, Ildikó Szikossy, Tamás Hajdu, Vyacheslav Moiseyev, Andrey Gromov, Gunita Zariņa, Eran Meshorer, Liran Carmel, Ron Pinhasi
Publikováno v:
Genome Biology, Vol 25, Iss 1, Pp 1-23 (2024)
Abstract Reconstructing premortem DNA methylation levels in ancient DNA has led to breakthrough studies such as the prediction of anatomical features of the Denisovan. These studies rely on computationally inferring methylation levels from damage sig
Externí odkaz:
https://doaj.org/article/02bbf141ab6b403e817691f1389c919c
Solving symbolic reasoning problems that require compositionality and systematicity is considered one of the key ingredients of human intelligence. However, symbolic reasoning is still a great challenge for deep learning models, which often cannot ge
Externí odkaz:
http://arxiv.org/abs/2306.17249
Identifying molecules that exhibit some pre-specified properties is a difficult problem to solve. In the last few years, deep generative models have been used for molecule generation. Deep Graph Variational Autoencoders are among the most powerful ma
Externí odkaz:
http://arxiv.org/abs/2305.11699
Using only image-sentence pairs, weakly-supervised visual-textual grounding aims to learn region-phrase correspondences of the respective entity mentions. Compared to the supervised approach, learning is more difficult since bounding boxes and textua
Externí odkaz:
http://arxiv.org/abs/2305.10913
Autor:
Sara Salgues, Amélie Jacquot, Dominique Makowski, Chainez Tahar, Justine Baekeland, Margherita Arcangeli, Jérôme Dokic, Pascale Piolino, Marco Sperduti
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-11 (2024)
Abstract Traditional philosophical inquiry, and more recently neuroscientific studies, have investigated the sources of artworks' aesthetic appeal. A substantial effort has been made to isolate the objective features contributing to aesthetic appreci
Externí odkaz:
https://doaj.org/article/ea1cd0605ad0436a902cf66a1237a3bc
Autor:
Aldo Morrone, Elva Abril, Ilaria Cavallo, Francesca Sivori, Isabella Sperduti, Viviana Lora, Giovanna D'Agosto, Elisabetta Trento, Martina Pontone, Arianna Mastrofrancesco, Abraham Getachew Kelbore, Frehiwot Daba Gutema, Adel Sammain, Ottavio Latini, Enea Gino Di Domenico, Fulvia Pimpinelli
Publikováno v:
JEADV Clinical Practice, Vol 3, Iss 3, Pp 827-835 (2024)
Abstract Background Patients with human immunodeficiency virus (HIV) infection may present a large variety of skin manifestations, often associated with significant morbidity. In turn, dermatological diseases may represent an early sign of HIV infect
Externí odkaz:
https://doaj.org/article/46cd72d9ef3a412b91f2be962b3f7122