Zobrazeno 1 - 10
of 200
pro vyhledávání: '"Cagliero, Luca"'
Large Language Models (LLMs) have demonstrated impressive performance across various tasks. However, current training approaches combine standard cross-entropy loss with extensive data, human feedback, or ad hoc methods to enhance performance. These
Externí odkaz:
http://arxiv.org/abs/2409.13641
Autor:
Napolitano, Davide, Cagliero, Luca
Shapley Values are concepts established for eXplainable AI. They are used to explain black-box predictive models by quantifying the features' contributions to the model's outcomes. Since computing the exact Shapley Values is known to be computational
Externí odkaz:
http://arxiv.org/abs/2407.16482
Autor:
La Quatra, Moreno, Koudounas, Alkis, Vaiani, Lorenzo, Baralis, Elena, Cagliero, Luca, Garza, Paolo, Siniscalchi, Sabato Marco
Limited diversity in standardized benchmarks for evaluating audio representation learning (ARL) methods may hinder systematic comparison of current methods' capabilities. We present ARCH, a comprehensive benchmark for evaluating ARL methods on divers
Externí odkaz:
http://arxiv.org/abs/2405.00934
Autor:
Ding, Yihao, Vaiani, Lorenzo, Han, Caren, Lee, Jean, Garza, Paolo, Poon, Josiah, Cagliero, Luca
This paper presents a groundbreaking multimodal, multi-task, multi-teacher joint-grained knowledge distillation model for visually-rich form document understanding. The model is designed to leverage insights from both fine-grained and coarse-grained
Externí odkaz:
http://arxiv.org/abs/2402.17983
Summarizing multiple disaster-relevant data streams simultaneously is particularly challenging as existing Retrieve&Re-ranking strategies suffer from the inherent redundancy of multi-stream data and limited scalability in a multi-query setting. This
Externí odkaz:
http://arxiv.org/abs/2401.06683
The Document-based Visual Question Answering competition addresses the automatic detection of parent-child relationships between elements in multi-page documents. The goal is to identify the document elements that answer a specific question posed in
Externí odkaz:
http://arxiv.org/abs/2310.09432
Autor:
Koudounas, Alkis, La Quatra, Moreno, Vaiani, Lorenzo, Colomba, Luca, Attanasio, Giuseppe, Pastor, Eliana, Cagliero, Luca, Baralis, Elena
Recent large-scale Spoken Language Understanding datasets focus predominantly on English and do not account for language-specific phenomena such as particular phonemes or words in different lects. We introduce ITALIC, the first large-scale speech dat
Externí odkaz:
http://arxiv.org/abs/2306.08502
Autor:
Vaiani, Lorenzo1 (AUTHOR) lorenzo.vaiani@polito.it, Cagliero, Luca1 (AUTHOR), Garza, Paolo1 (AUTHOR) paolo.garza@polito.it
Publikováno v:
Future Internet. Jul2024, Vol. 16 Issue 7, p247. 17p.
Publikováno v:
In Expert Systems With Applications 1 December 2024 255 Part B
Publikováno v:
In Expert Systems With Applications 15 April 2023 216