Zobrazeno 1 - 10
of 17 951
pro vyhledávání: '"Dinu, A."'
Autor:
Dinu, Catalin-Viorel, Moerland, Thomas
Quantum Tiq-Taq-Toe is a well-known benchmark and playground for both quantum computing and machine learning. Despite its popularity, no reinforcement learning (RL) methods have been applied to Quantum Tiq-Taq-Toe. Although there has been some resear
Externí odkaz:
http://arxiv.org/abs/2411.06429
Understanding animal vocalizations through multi-source data fusion is crucial for assessing emotional states and enhancing animal welfare in precision livestock farming. This study aims to decode dairy cow contact calls by employing multi-modal data
Externí odkaz:
http://arxiv.org/abs/2411.00477
Autor:
Bucur, Ana-Maria, Moldovan, Andreea-Codrina, Parvatikar, Krutika, Zampieri, Marcos, KhudaBukhsh, Ashiqur R., Dinu, Liviu P.
Computational approaches to predicting mental health conditions in social media have been substantially explored in the past years. Multiple surveys have been published on this topic, providing the community with comprehensive accounts of the researc
Externí odkaz:
http://arxiv.org/abs/2410.08793
In this paper we revisit the likelihood geometry of Gaussian graphical models. We give a detailed proof that the ML-degree behaves monotonically on induced subgraphs. Furthermore, we complete a missing argument that the ML-degree of the $n$-th cycle
Externí odkaz:
http://arxiv.org/abs/2410.07007
Autor:
Dinu, Marius-Constantin
As artificial intelligence (AI) systems advance, we move towards broad AI: systems capable of performing well on diverse tasks, understanding context, and adapting rapidly to new scenarios. A central challenge for broad AI systems is to generalize ov
Externí odkaz:
http://arxiv.org/abs/2410.06235
The Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES) is one of the most advanced algorithms in numerical black-box optimization. For noisy objective functions, several approaches were proposed to mitigate the noise, e.g., re-evaluations of
Externí odkaz:
http://arxiv.org/abs/2409.16757
Autor:
Patel, Ajay, Hofmarcher, Markus, Leoveanu-Condrei, Claudiu, Dinu, Marius-Constantin, Callison-Burch, Chris, Hochreiter, Sepp
Training models to act as agents that can effectively navigate and perform actions in a complex environment, such as a web browser, has typically been challenging due to lack of training data. Large language models (LLMs) have recently demonstrated s
Externí odkaz:
http://arxiv.org/abs/2405.20309
Autor:
Dinu, Rodica Andreea, Vodička, Martin
Jukes-Cantor model is one of the most meaningful statistical models from a biological perspective. We are interested in computing the algebraic degrees for phylogenetic varieties, which we call phylogenetic degrees, associated to the Jukes-Cantor mod
Externí odkaz:
http://arxiv.org/abs/2405.20184
This paper describes the approach of the UniBuc - NLP team in tackling the SemEval 2024 Task 8: Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection. We explored transformer-based and hybrid deep learning architect
Externí odkaz:
http://arxiv.org/abs/2405.17964
Autor:
Creanga, Claudiu, Dinu, Liviu P.
This paper outlines the approach of the ISDS-NLP team in the SemEval 2024 Task 10: Emotion Discovery and Reasoning its Flip in Conversation (EDiReF). For Subtask 1 we obtained a weighted F1 score of 0.43 and placed 12 in the leaderboard. We investiga
Externí odkaz:
http://arxiv.org/abs/2405.11222