Zobrazeno 1 - 10
of 1 661
pro vyhledávání: '"A. Dascălu"'
Natural Language Inference (NLI) evaluation is crucial for assessing language understanding models; however, popular datasets suffer from systematic spurious correlations that artificially inflate actual model performance. To address this, we propose
Externí odkaz:
http://arxiv.org/abs/2410.03429
Autor:
Masala, Mihai, Ilie-Ablachim, Denis C., Dima, Alexandru, Corlatescu, Dragos, Zavelca, Miruna, Olaru, Ovio, Terian, Simina, Terian, Andrei, Leordeanu, Marius, Velicu, Horia, Popescu, Marius, Dascalu, Mihai, Rebedea, Traian
In recent years, Large Language Models (LLMs) have achieved almost human-like performance on various tasks. While some LLMs have been trained on multilingual data, most of the training data is in English; hence, their performance in English greatly e
Externí odkaz:
http://arxiv.org/abs/2406.18266
Autor:
Wu, Rui, Feil-Seifer, David J, Shill, Ponkoj C, Jamali, Hossein, Dascalu, Sergiu, Harris, Fred, Rosof, Laura, Hutchins, Bryan, Ringler, Marjorie Campo, Zhu, Zhen
Recent advancements in robotics, including applications like self-driving cars, unmanned systems, and medical robots, have had a significant impact on the job market. On one hand, big robotics companies offer training programs based on the job requir
Externí odkaz:
http://arxiv.org/abs/2406.07928
Autor:
Masala, Mihai, Ilie-Ablachim, Denis C., Corlatescu, Dragos, Zavelca, Miruna, Leordeanu, Marius, Velicu, Horia, Popescu, Marius, Dascalu, Mihai, Rebedea, Traian
In recent years, Large Language Models (LLMs) have achieved almost human-like performance on various tasks. While some LLMs have been trained on multilingual data, most of the training data is in English. Hence, their performance in English greatly e
Externí odkaz:
http://arxiv.org/abs/2405.07703
In today's world, where moving forward hinges on innovation and working together, this article introduces a new global online platform that is all about sparking teamwork to come up with new ideas. This platform goes beyond borders and barriers betwe
Externí odkaz:
http://arxiv.org/abs/2402.12718
Publikováno v:
Sci Rep 14, 15909 (2024)
Transformers have achieved remarkable performance in multivariate time series(MTS) forecasting due to their capability to capture long-term dependencies. However, the canonical attention mechanism has two key limitations: (1) its quadratic time compl
Externí odkaz:
http://arxiv.org/abs/2312.06874
Autor:
Paraschiv, Andrei, Dascalu, Mihai
Conspiracy theories have become a prominent and concerning aspect of online discourse, posing challenges to information integrity and societal trust. As such, we address conspiracy theory detection as proposed by the ACTI @ EVALITA 2023 shared task.
Externí odkaz:
http://arxiv.org/abs/2309.16275
Autor:
Jamali, Hossein, Shill, Ponkoj Chandra, Feil-Seifer, David, Harris, Jr., Frederick C., Dascalu, Sergiu M.
Cloud computing is a concept introduced in the information technology era, with the main components being the grid, distributed, and valuable computing. The cloud is being developed continuously and, naturally, comes up with many challenges, one of w
Externí odkaz:
http://arxiv.org/abs/2309.09441
Autor:
Shill, Ponkoj Chandra, Wu, Rui, Jamali, Hossein, Hutchins, Bryan, Dascalu, Sergiu, Harris, Frederick C., Feil-Seifer, David
Publikováno v:
2023 IEEE Frontiers in Education Conference (FIE)
This paper presents a work-in-progress on a learn-ing system that will provide robotics students with a personalized learning environment. This addresses both the scarcity of skilled robotics instructors, particularly in community colleges and the ex
Externí odkaz:
http://arxiv.org/abs/2309.05124
Publikováno v:
Annals: Series on engineering sciences (Academy of Romanian Scientists), Vol 16, Iss 2, Pp 31-40 (2024)
Industry 4.0 technology coordinates intelligent equipment throughout the manufacturing process, and Lean Six Sigma (LSS) improves production efficiency and effectiveness. The marriage of Lean Six Sigma and Industry 4.0 makes for a solid partnershi
Externí odkaz:
https://doaj.org/article/b40f438521b2426ea159485769bb3c38
