Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Tang, Xunzhu"'
Autor:
Zhu, Dongsheng, Tang, Xunzhu, Han, Weidong, Lu, Jinghui, Zhao, Yukun, Xing, Guoliang, Wang, Junfeng, Yin, Dawei
This paper presents VisLingInstruct, a novel approach to advancing Multi-Modal Language Models (MMLMs) in zero-shot learning. Current MMLMs show impressive zero-shot abilities in multi-modal tasks, but their performance depends heavily on the quality
Externí odkaz:
http://arxiv.org/abs/2402.07398
Autor:
Song, Yewei, Ezzini, Saad, Tang, Xunzhu, Lothritz, Cedric, Klein, Jacques, Bissyandé, Tegawendé, Boytsov, Andrey, Ble, Ulrick, Goujon, Anne
Text-to-SQL, the task of translating natural language questions into SQL queries, is part of various business processes. Its automation, which is an emerging challenge, will empower software practitioners to seamlessly interact with relational databa
Externí odkaz:
http://arxiv.org/abs/2312.14725
Autor:
Zhou, Xiaofan, Tang, Xunzhu
The target of Electronic Health Record (EHR) coding is to find the diagnostic codes according to the EHRs. In previous research, researchers have preferred to do multi-classification on the EHR coding task; most of them encode the EHR first and then
Externí odkaz:
http://arxiv.org/abs/2312.10259
In the face of growing vulnerabilities found in open-source software, the need to identify {discreet} security patches has become paramount. The lack of consistency in how software providers handle maintenance often leads to the release of security p
Externí odkaz:
http://arxiv.org/abs/2312.01241
Autor:
Tang, Xunzhu, Chen, Zhenghan, Ezzini, Saad, Tian, Haoye, Klein, Jacques, Bissyande, Tegawende F.
In recent years, patch representation learning has emerged as a necessary research direction for exploiting the capabilities of machine learning in software generation. These representations have driven significant performance enhancements across a v
Externí odkaz:
http://arxiv.org/abs/2310.12753
Autor:
Tang, Xunzhu, Tian, Haoye, Chen, Zhenghan, Pian, Weiguo, Ezzini, Saad, Kabore, Abdoul Kader, Habib, Andrew, Klein, Jacques, Bissyande, Tegawende F.
Patch representation is crucial in automating various software engineering tasks, like determining patch accuracy or summarizing code changes. While recent research has employed deep learning for patch representation, focusing on token sequences or A
Externí odkaz:
http://arxiv.org/abs/2308.16586
Autor:
Tang, Xunzhu, Chen, zhenghan, Ezzini, Saad, Tian, Haoye, Song, Yewei, Klein, Jacques, Bissyande, Tegawende F.
Within the realm of advanced code retrieval, existing methods have primarily relied on intricate matching and attention-based mechanisms. However, these methods often lead to computational and memory inefficiencies, posing a significant challenge to
Externí odkaz:
http://arxiv.org/abs/2308.15234
Autor:
Tang, Xunzhu, Chen, zhenghan, Ezzini, Saad, Tian, Haoye, Song, Yewei, Klein, Jacques, Bissyande, Tegawende F.
The growth of open-source software has increased the risk of hidden vulnerabilities that can affect downstream software applications. This concern is further exacerbated by software vendors' practice of silently releasing security patches without exp
Externí odkaz:
http://arxiv.org/abs/2308.15233
Commit message generation (CMG) is a challenging task in automated software engineering that aims to generate natural language descriptions of code changes for commits. Previous methods all start from the modified code snippets, outputting commit mes
Externí odkaz:
http://arxiv.org/abs/2308.00147
Autor:
Zhou, Xiaofan, Tang, Xunzhu
Electronic Health Record (EHR) coding involves automatically classifying EHRs into diagnostic codes. While most previous research treats this as a multi-label classification task, generating probabilities for each code and selecting those above a cer
Externí odkaz:
http://arxiv.org/abs/2305.13250