Zobrazeno 1 - 10
of 192
pro vyhledávání: '"Liu Bingquan"'
Publikováno v:
矿业科学学报, Vol 7, Iss 4, Pp 474-480 (2022)
Due to the exploitation of mineral resources in the deep underground space, it is more and more important to study the variation trend of deep in-situ stress field. In recent years the researches have updated many in-situ stress data. It is necessary
Externí odkaz:
https://doaj.org/article/481f674522be41dabff75519c469de02
The projector plays a crucial role in multi-modal language models (MLLMs). The number of visual tokens it outputs affects the efficiency of the MLLM, while the quality of the visual tokens influences the visual understanding capabilities of the MLLM.
Externí odkaz:
http://arxiv.org/abs/2410.10319
Publikováno v:
矿业科学学报, Vol 3, Iss 6, Pp 527-535 (2018)
A large number of energy can be released in coal bumps.In order to quantitatively calculate energy released amount, the uniaxial compression single-pressure experiment of coal briquette model was carried out, and the ejection velocity of coal pillar
Externí odkaz:
https://doaj.org/article/387ca22f1b84446f9ccb9bdfc89325fe
Publikováno v:
矿业科学学报, Vol 2, Iss 6, Pp 550-558 (2017)
In order to solve the multiplexing problem of gob-side entry retaining, the analytic hierarchy process(AHP) and the matter-element evaluation were applied to establish a multi-hierarchy and multi-index comprehensive evaluation model of surrounding ro
Externí odkaz:
https://doaj.org/article/7930b4738cdc47ecb56769ad5ed45a79
Autor:
Li, Shaobo, Li, Xiaoguang, Shang, Lifeng, Sun, Chengjie, Liu, Bingquan, Ji, Zhenzhou, Jiang, Xin, Liu, Qun
Previous works show that Pre-trained Language Models (PLMs) can capture factual knowledge. However, some analyses reveal that PLMs fail to perform it robustly, e.g., being sensitive to the changes of prompts when extracting factual knowledge. To miti
Externí odkaz:
http://arxiv.org/abs/2210.11165
Autor:
Li, Shaobo, Li, Xiaoguang, Shang, Lifeng, Dong, Zhenhua, Sun, Chengjie, Liu, Bingquan, Ji, Zhenzhou, Jiang, Xin, Liu, Qun
Recently, there has been a trend to investigate the factual knowledge captured by Pre-trained Language Models (PLMs). Many works show the PLMs' ability to fill in the missing factual words in cloze-style prompts such as "Dante was born in [MASK]." Ho
Externí odkaz:
http://arxiv.org/abs/2203.16747
Publikováno v:
In Journal of Cleaner Production 1 November 2024 478
Autor:
Li, Shaobo, Liu, Qun, Jiang, Xin, Yin, Yichun, Sun, Chengjie, Liu, Bingquan, Ji, Zhenzhou, Shang, Lifeng
Human-designed rules are widely used to build industry applications. However, it is infeasible to maintain thousands of such hand-crafted rules. So it is very important to integrate the rule knowledge into neural networks to build a hybrid model that
Externí odkaz:
http://arxiv.org/abs/2109.02882
Autor:
Li, Shaobo, Li, Xiaoguang, Shang, Lifeng, Jiang, Xin, Liu, Qun, Sun, Chengjie, Ji, Zhenzhou, Liu, Bingquan
Collecting supporting evidence from large corpora of text (e.g., Wikipedia) is of great challenge for open-domain Question Answering (QA). Especially, for multi-hop open-domain QA, scattered evidence pieces are required to be gathered together to sup
Externí odkaz:
http://arxiv.org/abs/2012.15534
Publikováno v:
In Expert Systems With Applications 15 December 2023 233