Zobrazeno 1 - 10
of 3 947
pro vyhledávání: '"Huang Kuan"'
Autor:
Jiang Kai-xuan, Zhou Yan-jun, Yang Ran, Song Ke-xing, Liu Ya-hui, Zhang Yan-min, Yang Shao-dan, Zhou Fei, Huang Kuan, Liu Dong-dong, Yang Wen-hao
Publikováno v:
Journal of Materials Research and Technology, Vol 27, Iss , Pp 2201-2215 (2023)
The Cu–15Ni–8Sn alloy ingot was prepared in the medium-frequency induction melting furnace. The hot extruded alloy was treated by solid solution at 840 °C for 60 min and aging at 400 °C for different times (0 miñ480 min). The effect of aging t
Externí odkaz:
https://doaj.org/article/8f2b9e5354fb480a9ec40873d0a48ca4
Autor:
Kumar Yulia, Huang Kuan, Gordon Zachary, Castro Lais, Okumu Egan, Morreale Patricia, Li J. Jenny
Publikováno v:
ITM Web of Conferences, Vol 60, p 00004 (2024)
The study explores the transformative capabilities of Transformers and Large Language Models (LLMs) in the early detection of Acute Lymphoblastic Leukaemia (ALL). The researchers benchmark Vision Transformers with Deformable Attention (DAT) and Hiera
Externí odkaz:
https://doaj.org/article/742df88e54dd455db433027302580db2
Autor:
Chen, Shengjia, Campanella, Gabriele, Elmas, Abdulkadir, Stock, Aryeh, Zeng, Jennifer, Polydorides, Alexandros D., Schoenfeld, Adam J., Huang, Kuan-lin, Houldsworth, Jane, Vanderbilt, Chad, Fuchs, Thomas J.
Recent advances in artificial intelligence (AI), in particular self-supervised learning of foundation models (FMs), are revolutionizing medical imaging and computational pathology (CPath). A constant challenge in the analysis of digital Whole Slide I
Externí odkaz:
http://arxiv.org/abs/2407.07841
Autor:
Campanella, Gabriele, Chen, Shengjia, Verma, Ruchika, Zeng, Jennifer, Stock, Aryeh, Croken, Matt, Veremis, Brandon, Elmas, Abdulkadir, Huang, Kuan-lin, Kwan, Ricky, Houldsworth, Jane, Schoenfeld, Adam J., Vanderbilt, Chad
The use of self-supervised learning (SSL) to train pathology foundation models has increased substantially in the past few years. Notably, several models trained on large quantities of clinical data have been made publicly available in recent months.
Externí odkaz:
http://arxiv.org/abs/2407.06508
Autor:
Wang, Ziqi, Zhang, Hanlin, Li, Xiner, Huang, Kuan-Hao, Han, Chi, Ji, Shuiwang, Kakade, Sham M., Peng, Hao, Ji, Heng
Position bias has proven to be a prevalent issue of modern language models (LMs), where the models prioritize content based on its position within the given context. This bias often leads to unexpected model failures and hurts performance, robustness
Externí odkaz:
http://arxiv.org/abs/2407.01100
This research explores how the information of prompts interacts with the high-performing speech recognition model, Whisper. We compare its performances when prompted by prompts with correct information and those corrupted with incorrect information.
Externí odkaz:
http://arxiv.org/abs/2406.05806
Autor:
Ritter-Gutierrez, Fabian, Huang, Kuan-Po, Wong, Jeremy H. M, Ng, Dianwen, Lee, Hung-yi, Chen, Nancy F., Chng, Eng Siong
Deep learning models for speech rely on large datasets, presenting computational challenges. Yet, performance hinges on training data size. Dataset Distillation (DD) aims to learn a smaller dataset without much performance degradation when training w
Externí odkaz:
http://arxiv.org/abs/2406.02963
Recent advancements in multimodal large language models (LLMs) have shown their potential in various domains, especially concept reasoning. Despite these developments, applications in understanding 3D environments remain limited. This paper introduce
Externí odkaz:
http://arxiv.org/abs/2405.17427
Autor:
Wang, Zhenhailong, Hsu, Joy, Wang, Xingyao, Huang, Kuan-Hao, Li, Manling, Wu, Jiajun, Ji, Heng
While large multimodal models excel in broad vision-language benchmarks, they often struggle with tasks requiring precise perception of low-level visual details, such as comparing line lengths or solving simple mazes. In particular, this failure mode
Externí odkaz:
http://arxiv.org/abs/2404.06479
Autor:
Parekh, Tanmay, Mac, Anh, Yu, Jiarui, Dong, Yuxuan, Shahriar, Syed, Liu, Bonnie, Yang, Eric, Huang, Kuan-Hao, Wang, Wei, Peng, Nanyun, Chang, Kai-Wei
Social media is an easy-to-access platform providing timely updates about societal trends and events. Discussions regarding epidemic-related events such as infections, symptoms, and social interactions can be crucial for informing policymaking during
Externí odkaz:
http://arxiv.org/abs/2404.01679