Zobrazeno 1 - 10
of 3 099
pro vyhledávání: '"Razeghi, P."'
Humans have the ability to reason about geometric patterns in images and scenes from a young age. However, developing large multimodal models (LMMs) capable of similar reasoning remains a challenge, highlighting the need for robust evaluation methods
Externí odkaz:
http://arxiv.org/abs/2411.00264
Large language models (LLMs) require alignment, such as instruction-tuning or reinforcement learning from human feedback, to effectively and safely follow user instructions. This process necessitates training aligned versions for every model size in
Externí odkaz:
http://arxiv.org/abs/2410.09300
In this paper, we investigate the potential of image-to-image translation (I2I) techniques for transferring realism to 3D-rendered facial images in the context of Face Recognition (FR) systems. The primary motivation for using 3D-rendered facial imag
Externí odkaz:
http://arxiv.org/abs/2407.07627
Gender bias research has been pivotal in revealing undesirable behaviors in large language models, exposing serious gender stereotypes associated with occupations, and emotions. A key observation in prior work is that models reinforce stereotypes as
Externí odkaz:
http://arxiv.org/abs/2405.00588
In this study, we apply the information-theoretic Privacy Funnel (PF) model to the domain of face recognition, developing a novel method for privacy-preserving representation learning within an end-to-end training framework. Our approach addresses th
Externí odkaz:
http://arxiv.org/abs/2404.02696
Autor:
Razeghi, Mohammadali, Spiece, Jean, Fonck, Valentin, Zhang, Yao, Rohde, Michael, Joris, Rikkie, Dobson, Philip S., Weaver, Jonathan M. R., Pereira, Lino da Costa, Granville, Simon, Gehring, Pascal
Solid-state cooling devices offer compact, quiet, reliable and environmentally friendly solutions that currently rely primarily on the thermoelectric (TE) effect. Despite more than two centuries of research, classical thermoelectric coolers suffer fr
Externí odkaz:
http://arxiv.org/abs/2403.13598
In this study, we harness the information-theoretic Privacy Funnel (PF) model to develop a method for privacy-preserving representation learning using an end-to-end training framework. We rigorously address the trade-off between obfuscation and utili
Externí odkaz:
http://arxiv.org/abs/2401.14792
Autor:
Zahra Yari, Samira Ebrahimof, Samira Soltanieh, Marieh Salavatizadeh, Sara Karimi, Sussan K. Ardestani, Mohammadreza Salehi, Soodeh Razeghi Jahromi, Tooba Ghazanfari, Azita Hekmatdoost
Publikováno v:
Journal of Nutrition and Food Security, Vol 9, Iss 4, Pp 702-711 (2024)
Increased serum concentrations of inflammatory biomarkers in patients indicate a strong association between COVID-19 and inflammation. However, the association between diet-related inflammation and COVID-19 has been less investigated. The aim of this
Externí odkaz:
https://doaj.org/article/235bf71fd42f46158efa2599470de102
Language models are achieving impressive performance on various tasks by aggressively adopting inference-time prompting techniques, such as zero-shot and few-shot prompting. In this work, we introduce EchoPrompt, a simple yet effective approach that
Externí odkaz:
http://arxiv.org/abs/2309.10687
Autor:
Nottingham, Kolby, Razeghi, Yasaman, Kim, Kyungmin, Lanier, JB, Baldi, Pierre, Fox, Roy, Singh, Sameer
Large language models (LLMs) are being applied as actors for sequential decision making tasks in domains such as robotics and games, utilizing their general world knowledge and planning abilities. However, previous work does little to explore what en
Externí odkaz:
http://arxiv.org/abs/2307.11922