Zobrazeno 1 - 10
of 1 484
pro vyhledávání: '"Entezari, P."'
Inference for Large Language Models (LLMs) is computationally demanding. To reduce the cost of auto-regressive decoding, Key-Value (KV) caching is used to store intermediate activations, enabling GPUs to perform only the incremental computation requi
Externí odkaz:
http://arxiv.org/abs/2411.17089
Recent text-to-image models like Stable Diffusion produce photo-realistic images but often show demographic biases. Previous debiasing methods focused on training-based approaches, failing to explore the root causes of bias and overlooking Stable Dif
Externí odkaz:
http://arxiv.org/abs/2408.12692
Deep learning recommendation models (DLRMs) are at the heart of the current e-commerce industry. However, the amount of training data used to train these large models is growing exponentially, leading to substantial training hurdles. The training dat
Externí odkaz:
http://arxiv.org/abs/2407.08108
Autor:
Esser, Patrick, Kulal, Sumith, Blattmann, Andreas, Entezari, Rahim, Müller, Jonas, Saini, Harry, Levi, Yam, Lorenz, Dominik, Sauer, Axel, Boesel, Frederic, Podell, Dustin, Dockhorn, Tim, English, Zion, Lacey, Kyle, Goodwin, Alex, Marek, Yannik, Rombach, Robin
Diffusion models create data from noise by inverting the forward paths of data towards noise and have emerged as a powerful generative modeling technique for high-dimensional, perceptual data such as images and videos. Rectified flow is a recent gene
Externí odkaz:
http://arxiv.org/abs/2403.03206
Autor:
Mehrdad Hashemi, Asal Abolghasemi Fard, Bita Pakshad, Pezhman Shafiei Asheghabadi, Amineh Hosseinkhani, Atena Sadat Hosseini, Parham Moradi, Mohammadreza Mohammadbeygi Niye, Ghazal Najafi, Mohadeseh Farahzadi, Saloomeh Khoushab, Afshin Taheriazam, Najma Farahani, Mahya Mohammadi, Salman Daneshi, Noushin Nabavi, Maliheh Entezari
Publikováno v:
Non-coding RNA Research, Vol 11, Iss , Pp 1-21 (2025)
Lung cancer (LC) is one of the most common causes of cancer-related death worldwide. It has been demonstrated that the prognosis of current drug treatments is affected by a variety of factors, including late stage, tumor recurrence, inaccessibility t
Externí odkaz:
https://doaj.org/article/7177f746362c4d9ca2433bd15b6dd531
Autor:
Mehrdad Hashemi, Elaheh Mohandesi Khosroshahi, Pouria Daneii, Aria Hassanpoor, Maedeh Eslami, Zeinab Khazaei Koohpar, Saba Asadi, Abbas Zabihi, Behdokht Jamali, Amin Ghorbani, Noushin Nabavi, Mohammad Reza Memarkashani, Shokooh Salimimoghadam, Afshin Taheriazam, Shing Cheng Tan, Maliheh Entezari, Najma Farahani, Kiavash Hushmandi
Publikováno v:
Non-coding RNA Research, Vol 10, Iss , Pp 98-115 (2025)
The complex interplay of epigenetic factors is essential in regulating the hallmarks of cancer and orchestrating intricate molecular interactions during tumor progression. Circular RNAs (circRNAs), known for their covalently closed loop structures, a
Externí odkaz:
https://doaj.org/article/29e4252f83fa4c9e846c3fce5296f5ee
Autor:
Mehrdad Hashemi, Elaheh Mohandesi Khosroshahi, Saba Asadi, Mahsa Tanha, Forough Ghatei Mohseni, Ramina Abdolmohammad Sagha, Elham Taheri, Paria Vazayefi, Helya Shekarriz, Fatemeh Habibi, Shaghayegh Mortazi, Ramin Khorrami, Noushin Nabavi, Mohsen Rashidi, Afshin Taheriazam, Payman Rahimzadeh, Maliheh Entezari
Publikováno v:
Non-coding RNA Research, Vol 10, Iss , Pp 1-15 (2025)
Cancer progression results from the dysregulation of molecular pathways, each with unique features that can either promote or inhibit tumor growth. The complexity of carcinogenesis makes it challenging for researchers to target all pathways in cancer
Externí odkaz:
https://doaj.org/article/ffc373024d574d789b422039da6e9a98
Publikováno v:
مجله علوم پزشکی فیض (پیوسته), Vol 28, Iss 3, Pp 307-316 (2024)
Background and Aim: Identifying key genes involved in the development of gastrointestinal cancers is crucial for understanding the molecular mechanisms underlying these diseases and for developing effective therapeutic and diagnostic strategies. Memb
Externí odkaz:
https://doaj.org/article/4cace27dd4154ebb84e0571655b88c8f
Autor:
Gadre, Samir Yitzhak, Ilharco, Gabriel, Fang, Alex, Hayase, Jonathan, Smyrnis, Georgios, Nguyen, Thao, Marten, Ryan, Wortsman, Mitchell, Ghosh, Dhruba, Zhang, Jieyu, Orgad, Eyal, Entezari, Rahim, Daras, Giannis, Pratt, Sarah, Ramanujan, Vivek, Bitton, Yonatan, Marathe, Kalyani, Mussmann, Stephen, Vencu, Richard, Cherti, Mehdi, Krishna, Ranjay, Koh, Pang Wei, Saukh, Olga, Ratner, Alexander, Song, Shuran, Hajishirzi, Hannaneh, Farhadi, Ali, Beaumont, Romain, Oh, Sewoong, Dimakis, Alex, Jitsev, Jenia, Carmon, Yair, Shankar, Vaishaal, Schmidt, Ludwig
Multimodal datasets are a critical component in recent breakthroughs such as Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model architectures or training algorithms. To address this shortcoming in the M
Externí odkaz:
http://arxiv.org/abs/2304.14108
Autor:
Entezari, Rahim, Wortsman, Mitchell, Saukh, Olga, Shariatnia, M. Moein, Sedghi, Hanie, Schmidt, Ludwig
The transfer learning paradigm of model pre-training and subsequent fine-tuning produces high-accuracy models. While most studies recommend scaling the pre-training size to benefit most from transfer learning, a question remains: what data and method
Externí odkaz:
http://arxiv.org/abs/2302.13602