Zobrazeno 1 - 10
of 41
pro vyhledávání: '"JIANG Minhao"'
Publikováno v:
Cailiao gongcheng, Vol 52, Iss 11, Pp 74-82 (2024)
Al-5%Fe-xNi alloys （x=0%，1.5%，5%，7.5%，10%， mass fraction，the same below） were prepared by the traditional casting method， and the morphology and size changes of the primary phase in the alloys after Ni addition were observed. The tr
Externí odkaz:
https://doaj.org/article/7cef52713338472bb3b6ef5be1dc9c27
Autor:
Ouyang, Siru, Wang, Shuohang, Jiang, Minhao, Zhong, Ming, Yu, Donghan, Han, Jiawei, Shen, Yelong
Speculative decoding stands as a pivotal technique to expedite inference in autoregressive (large) language models. This method employs a smaller draft model to speculate a block of tokens, which the target model then evaluates for acceptance. Despit
Externí odkaz:
http://arxiv.org/abs/2410.10141
Autor:
Jiang, Pengcheng, Xiao, Cao, Jiang, Minhao, Bhatia, Parminder, Kass-Hout, Taha, Sun, Jimeng, Han, Jiawei
Large language models (LLMs) have demonstrated significant potential in clinical decision support. Yet LLMs still suffer from hallucinations and lack fine-grained contextual medical knowledge, limiting their high-stake healthcare applications such as
Externí odkaz:
http://arxiv.org/abs/2410.04585
Autor:
Jiang, Minhao, Liu, Ken Ziyu, Zhong, Ming, Schaeffer, Rylan, Ouyang, Siru, Han, Jiawei, Koyejo, Sanmi
Language models pre-trained on web-scale corpora demonstrate impressive capabilities on diverse downstream tasks. However, there is increasing concern whether such capabilities might arise from evaluation datasets being included in the pre-training c
Externí odkaz:
http://arxiv.org/abs/2401.06059
Structured chemical reaction information plays a vital role for chemists engaged in laboratory work and advanced endeavors such as computer-aided drug design. Despite the importance of extracting structured reactions from scientific literature, data
Externí odkaz:
http://arxiv.org/abs/2307.01448
Weakly-supervised text classification trains a classifier using the label name of each target class as the only supervision, which largely reduces human annotation efforts. Most existing methods first use the label names as static keyword-based featu
Externí odkaz:
http://arxiv.org/abs/2305.13723
Fine-grained entity typing (FET), which assigns entities in text with context-sensitive, fine-grained semantic types, is a basic but important task for knowledge extraction from unstructured text. FET has been studied extensively in natural language
Externí odkaz:
http://arxiv.org/abs/2305.12307
Taxonomies are fundamental to many real-world applications in various domains, serving as structural representations of knowledge. To deal with the increasing volume of new concepts needed to be organized as taxonomies, researchers turn to automatica
Externí odkaz:
http://arxiv.org/abs/2202.04887
Publikováno v:
In Materials Today June 2024 75:57-70
Autor:
Zhu, Jiawei, You, Yawen, Zhang, Wenting, Wang, Wenjie, Jiang, Minhao, Pu, Fang, Ren, Jinsong, Qu, Xiaogang
Publikováno v:
In Nano Today April 2024 55