Zobrazeno 1 - 10
of 3 936
pro vyhledávání: '"Martínez, Maria P."'
Previous work has shown that training "helpful-only" LLMs with reinforcement learning on a curriculum of gameable environments can lead models to generalize to egregious specification gaming, such as editing their own reward function or modifying tas
Externí odkaz:
http://arxiv.org/abs/2410.06491
Autor:
Rago, Antonio, Martinez, Maria Vanina
As AI models become ever more complex and intertwined in humans' daily lives, greater levels of interactivity of explainable AI (XAI) methods are needed. In this paper, we propose the use of belief change theory as a formal foundation for operators t
Externí odkaz:
http://arxiv.org/abs/2408.06875
Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning. Traditional approaches typi
Externí odkaz:
http://arxiv.org/abs/2405.14020
Autor:
Coarasa, Iván, Amaré, Julio, Apilluelo, Jaime, Cebrián, Susana, Cintas, David, García, Eduardo, Martínez, María, Oliván, Miguel Ángel, Ortigoza, Ysrael, de Solórzano, Alfonso Ortiz, Pardo, Tamara, Puimedón, Jorge, Salinas, Ana, Sarsa, María Luisa, Villar, Patricia
Weakly interacting massive particles (WIMPs) are well-motivated candidates for dark matter. One signature of galactic WIMPs is the annual modulation expected in a detector's interaction rate, which arises from Earth's revolution around the Sun. Over
Externí odkaz:
http://arxiv.org/abs/2404.17348
Preferences are a pivotal component in practical reasoning, especially in tasks that involve decision-making over different options or courses of action that could be pursued. In this work, we focus on repairing and querying inconsistent knowledge ba
Externí odkaz:
http://arxiv.org/abs/2402.09265
Autor:
Cifuentes, Santiago, Bertossi, Leopoldo, Pardal, Nina, Abriola, Sergio, Martinez, Maria Vanina, Romero, Miguel
Attribution scores reflect how important the feature values in an input entity are for the output of a machine learning model. One of the most popular attribution scores is the SHAP score, which is an instantiation of the general Shapley value used i
Externí odkaz:
http://arxiv.org/abs/2401.12731
Publikováno v:
ImmunoInformatics, 2024
Recent advancements in immune sequencing and experimental techniques are generating extensive T cell receptor (TCR) repertoire data, enabling the development of models to predict TCR binding specificity. Despite the computational challenges due to th
Externí odkaz:
http://arxiv.org/abs/2312.16594
Autor:
Coarasa, Iván, Amaré, Julio, Apilluelo, Jaime, Cebrián, Susana, Cintas, David, García, Eduardo, Martínez, María, Oliván, Miguel Ángel, Ortigoza, Ysrael, de Solórzano, Alfonso Ortiz, Pardo, Tamara, Puimedón, Jorge, Salinas, Ana, Sarsa, María Luisa, Villar, Patricia
The ANAIS experiment is intended to search for dark matter annual modulation with ultrapure NaI(Tl) scintillators in order to provide a model independent confirmation or refutation of the long-standing DAMA/LIBRA positive annual modulation signal in
Externí odkaz:
http://arxiv.org/abs/2311.03392
Autor:
Garzon, Sandro Rodriguez, Tuan, Hai Dinh, Martinez, Maria Mora, Küpper, Axel, Einsiedler, Hans Joachim, Schneider, Daniela
Next generation mobile networks are poised to transition from monolithic structures owned and operated by single mobile network operators into multi-stakeholder networks where various parties contribute with infrastructure, resources, and services. H
Externí odkaz:
http://arxiv.org/abs/2310.19366
Protein interactions and assembly formation are fundamental to most biological processes. Predicting the assembly structure from constituent proteins -- referred to as the protein docking task -- is thus a crucial step in protein design applications.
Externí odkaz:
http://arxiv.org/abs/2310.06177