Zobrazeno 1 - 10
of 83 752
pro vyhledávání: '"A. Samira"'
Large pretrained vision-language models like CLIP have shown promising generalization capability, but may struggle in specialized domains (e.g., satellite imagery) or fine-grained classification (e.g., car models) where the visual concepts are unseen
Externí odkaz:
http://arxiv.org/abs/2410.23698
Large language models (LLMs) have demonstrated remarkable performance across various downstream tasks. However, the high computational and memory requirements of LLMs are a major bottleneck. To address this, parameter-efficient fine-tuning (PEFT) met
Externí odkaz:
http://arxiv.org/abs/2410.20777
Autor:
Azzaz, Riadh, Hurel, Valentin, Menard, Patrice, Jahazi, Mohammad, Kahou, Samira Ebrahimi, Moosavi-Khoonsari, Elmira
Publikováno v:
Submied to the journal of Steel Research Intenrnational in 2024 (under review)
The scrap-based electric arc furnace process is expected to capture a significant share of the steel market in the future due to its potential for reducing environmental impacts through steel recycling. However, managing impurities, particularly phos
Externí odkaz:
http://arxiv.org/abs/2410.19924
Autor:
Dhrubo, Mahir Shahriar, Akter, Samira, Shuaib, Anwarul Bashir, Tahmid, Md Toki, Hasan, Zahid, Islam, A. B. M. Alim Al
Efficient vectorization of hand-drawn cadastral maps, such as Mouza maps in Bangladesh, poses a significant challenge due to their complex structures. Current manual digitization methods are time-consuming and labor-intensive. Our study proposes a se
Externí odkaz:
http://arxiv.org/abs/2410.15961
Optimizing framerate for a given bitrate-spatial resolution pair in adaptive video streaming is essential to maintain perceptual quality while considering decoding complexity. Low framerates at low bitrates reduce compression artifacts and decrease d
Externí odkaz:
http://arxiv.org/abs/2410.00849
Machine Learning (ML) models are increasingly used to support or substitute decision making. In applications where skilled experts are a limited resource, it is crucial to reduce their burden and automate decisions when the performance of an ML model
Externí odkaz:
http://arxiv.org/abs/2409.20489
The rapid advancement of artificial intelligence systems has brought the challenge of AI alignment to the forefront of research, particularly in complex decision-making and task execution. As these systems surpass human-level performance in sophistic
Externí odkaz:
http://arxiv.org/abs/2409.07335
Autor:
Ali, Asad, Elghaayda, Samira, Al-Kuwari, Saif, Hussain, M. I., Rahim, M. T., Kuniyil, Hashir, Byrnes, Tim, Quach, James Q., Mansour, Mostafa, Haddadi, Saeed
We investigate a magnetic dipolar system influenced by Zeeman splitting, DM interaction, and KSEA exchange interaction, with an initial focus on quantum resource dynamics and a final application in modeling a quantum battery (QB). We analyze the effe
Externí odkaz:
http://arxiv.org/abs/2409.05000
Robotics can help address the growing worker shortage challenge of the manufacturing industry. As such, machine tending is a task collaborative robots can tackle that can also highly boost productivity. Nevertheless, existing robotics systems deploye
Externí odkaz:
http://arxiv.org/abs/2408.16875
Autor:
Guzelturk, Burak, Portner, Joshua, Ondry, Justin, Ghanbarzadeh, Samira, Tarantola, Mia, Jeong, Ahhyun, Field, Thomas, Chandler, Alicia M., Wieman, Eliza, Hopper, Thomas R., Watkins, Nicolas E., Yue, Jin, Cheng, Xinxin, Lin, Ming-Fu, Luo, Duan, Kramer, Patrick L., Shen, Xiaozhe, Reid, Alexander H., Borkiewicz, Olaf, Ruett, Uta, Zhang, Xiaoyi, Lindenberg, Aaron M., Ma, Jihong, Schaller, Richard, Talapin, Dmitri V., Cotts, Benjamin L.
Symmetry control is essential for realizing unconventional properties, such as ferroelectricity, nonlinear optical responses, and complex topological order, thus it holds promise for the design of emerging quantum and photonic systems. Nevertheless,
Externí odkaz:
http://arxiv.org/abs/2408.15464