Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Ezzini, Saad"'
Current video generation models excel at creating short, realistic clips, but struggle with longer, multi-scene videos. We introduce \texttt{DreamFactory}, an LLM-based framework that tackles this challenge. \texttt{DreamFactory} leverages multi-agen
Externí odkaz:
http://arxiv.org/abs/2408.11788
Autor:
Malaysha, Sanad, El-Haj, Mo, Ezzini, Saad, Khalilia, Mohammed, Jarrar, Mustafa, Almujaiwel, Sultan, Berrada, Ismail, Bouamor, Houda
The expanding financial markets of the Arab world require sophisticated Arabic NLP tools. To address this need within the banking domain, the Arabic Financial NLP (AraFinNLP) shared task proposes two subtasks: (i) Multi-dialect Intent Detection and (
Externí odkaz:
http://arxiv.org/abs/2407.09818
Navigating the complexities of language diversity is a central challenge in developing robust natural language processing systems, especially in specialized domains like banking. The Moroccan Dialect (Darija) serves as the common language that blends
Externí odkaz:
http://arxiv.org/abs/2405.16482
Autor:
Tang, Xunzhu, Kim, Kisub, Song, Yewei, Lothritz, Cedric, Li, Bei, Ezzini, Saad, Tian, Haoye, Klein, Jacques, Bissyande, Tegawende F.
Code review, which aims at ensuring the overall quality and reliability of software, is a cornerstone of software development. Unfortunately, while crucial, Code review is a labor-intensive process that the research community is looking to automate.
Externí odkaz:
http://arxiv.org/abs/2402.02172
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
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