Zobrazeno 1 - 10
of 3 639
pro vyhledávání: '"Arasteh A"'
Autor:
Mobarakeh, Niloufar Saeidi, Khamidehi, Behzad, Li, Chunlin, Mirkhani, Hamidreza, Arasteh, Fazel, Elmahgiubi, Mohammed, Zhang, Weize, Rezaee, Kasra, Poupart, Pascal
The primary goal of motion planning is to generate safe and efficient trajectories for vehicles. Traditionally, motion planning models are trained using imitation learning to mimic the behavior of human experts. However, these models often lack inter
Externí odkaz:
http://arxiv.org/abs/2412.05717
Autor:
Arasteh, Soroosh Tayebi, Lotfinia, Mahshad, Perez-Toro, Paula Andrea, Arias-Vergara, Tomas, Orozco-Arroyave, Juan Rafael, Schuster, Maria, Maier, Andreas, Yang, Seung Hee
Speech pathology has impacts on communication abilities and quality of life. While deep learning-based models have shown potential in diagnosing these disorders, the use of sensitive data raises critical privacy concerns. Although differential privac
Externí odkaz:
http://arxiv.org/abs/2409.19078
Autor:
Arasteh, Soroosh Tayebi, Lotfinia, Mahshad, Bressem, Keno, Siepmann, Robert, Ferber, Dyke, Kuhl, Christiane, Kather, Jakob Nikolas, Nebelung, Sven, Truhn, Daniel
Large language models (LLMs) have advanced the field of artificial intelligence (AI) in medicine. However LLMs often generate outdated or inaccurate information based on static training datasets. Retrieval augmented generation (RAG) mitigates this by
Externí odkaz:
http://arxiv.org/abs/2407.15621
Autor:
Arasteh, Fazel, Elmahgiubi, Mohammed, Khamidehi, Behzad, Mirkhani, Hamidreza, Zhang, Weize, Tongtong, Cao, Rezaee, Kasra
The planning problem constitutes a fundamental aspect of the autonomous driving framework. Recent strides in representation learning have empowered vehicles to comprehend their surrounding environments, thereby facilitating the integration of learnin
Externí odkaz:
http://arxiv.org/abs/2406.01544
Autor:
Karvandi, Mohammad Sina, Meghdadizanjani, Soroush, Arasteh, Sima, Monfared, Saleh Khalaj, Fallah, Mohammad K., Gorgin, Saeid, Lee, Jeong-A, van der Kouwe, Erik
Existing anti-malware software and reverse engineering toolkits struggle with stealthy sub-OS rootkits due to limitations of run-time kernel-level monitoring. A malicious kernel-level driver can bypass OS-level anti-virus mechanisms easily. Although
Externí odkaz:
http://arxiv.org/abs/2405.00298
Autor:
Arasteh, Soroosh Tayebi, Arias-Vergara, Tomas, Perez-Toro, Paula Andrea, Weise, Tobias, Packhaeuser, Kai, Schuster, Maria, Noeth, Elmar, Maier, Andreas, Yang, Seung Hee
Publikováno v:
Commun Med 4, (2024)
Integration of speech into healthcare has intensified privacy concerns due to its potential as a non-invasive biomarker containing individual biometric information. In response, speaker anonymization aims to conceal personally identifiable informatio
Externí odkaz:
http://arxiv.org/abs/2404.08064
Publikováno v:
Preventive Care in Nursing and Midwifery Journal, Vol 8, Iss 1, Pp 11-18 (2018)
Background: Despite the progress of family planning programs, a significant proportion of pregnancies are still unplanned which threatens the different dimensions of community health. Unplanned pregnancy affects parent's-child association. Maternal-f
Externí odkaz:
https://doaj.org/article/aa88632b6123445785ea8b6300d8588d
Autor:
Zhang, Weize, Elmahgiubi, Mohammed, Rezaee, Kasra, Khamidehi, Behzad, Mirkhani, Hamidreza, Arasteh, Fazel, Li, Chunlin, Kaleem, Muhammad Ahsan, Corral-Soto, Eduardo R., Sharma, Dhruv, Cao, Tongtong
In this paper we present the architecture of the Kyber-E2E submission to the map track of CARLA Leaderboard 2.0 Autonomous Driving (AD) challenge 2023, which achieved first place. We employed a modular architecture for our solution consists of five m
Externí odkaz:
http://arxiv.org/abs/2405.01394
Autor:
Arasteh, Bahman, Ghaffari, Ali
Publikováno v:
Data Technologies and Applications, 2024, Vol. 58, Issue 5, pp. 807-837.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/DTA-05-2023-0152
Autor:
Arasteh, Soroosh Tayebi, Kuhl, Christiane, Saehn, Marwin-Jonathan, Isfort, Peter, Truhn, Daniel, Nebelung, Sven
Publikováno v:
Sci Rep 13, 22576 (2023)
Developing robust artificial intelligence (AI) models that generalize well to unseen datasets is challenging and usually requires large and variable datasets, preferably from multiple institutions. In federated learning (FL), a model is trained colla
Externí odkaz:
http://arxiv.org/abs/2310.00757