Zobrazeno 1 - 10
of 13 039
pro vyhledávání: '"TIAN, Yuan"'
While fuzzing has demonstrated its effectiveness in exposing vulnerabilities within embedded firmware, the discovery of crashing test cases is only the first step in improving the security of these critical systems. The subsequent fault localization
Externí odkaz:
http://arxiv.org/abs/2410.18483
Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with human instructions. The primary goal during SFT is to select a small yet representative subset of training data from the larger pool, such that fine-tuning with th
Externí odkaz:
http://arxiv.org/abs/2410.09335
Autor:
Li, Chunyi, Zhang, Jianbo, Zhang, Zicheng, Wu, Haoning, Tian, Yuan, Sun, Wei, Lu, Guo, Liu, Xiaohong, Min, Xiongkuo, Lin, Weisi, Zhai, Guangtao
The outstanding performance of Large Multimodal Models (LMMs) has made them widely applied in vision-related tasks. However, various corruptions in the real world mean that images will not be as ideal as in simulations, presenting significant challen
Externí odkaz:
http://arxiv.org/abs/2410.05474
Large language models (LLMs) like GitHub Copilot and ChatGPT have emerged as powerful tools for code generation, significantly enhancing productivity and accelerating software development. However, existing benchmarks primarily focus on general code
Externí odkaz:
http://arxiv.org/abs/2409.15228
Unsupervised video semantic compression (UVSC), i.e., compressing videos to better support various analysis tasks, has recently garnered attention. However, the semantic richness of previous methods remains limited, due to the single semantic learnin
Externí odkaz:
http://arxiv.org/abs/2409.11718
Autor:
Liao, Zeyi, Mo, Lingbo, Xu, Chejian, Kang, Mintong, Zhang, Jiawei, Xiao, Chaowei, Tian, Yuan, Li, Bo, Sun, Huan
Generalist web agents have demonstrated remarkable potential in autonomously completing a wide range of tasks on real websites, significantly boosting human productivity. However, web tasks, such as booking flights, usually involve users' PII, which
Externí odkaz:
http://arxiv.org/abs/2409.11295
Though recent advances in machine learning have led to significant improvements in natural language interfaces for databases, the accuracy and reliability of these systems remain limited, especially in high-stakes domains. This paper introduces SQLuc
Externí odkaz:
http://arxiv.org/abs/2409.06178
Autor:
Song, Leo, Ding, Steven H. H., Tian, Yuan, Li, Li Tao, Charland, Philippe, Walenstein, Andrew
A Software Bill of Materials (SBoM) is a detailed inventory of all components, libraries, and modules in a software artifact, providing traceability throughout the software supply chain. With the increasing popularity of JavaScript in software engine
Externí odkaz:
http://arxiv.org/abs/2408.16198
Autor:
Wang, Long, Zhou, Lei-Ming, Tian, Yuan, Liu, Lyu-Hang, Guo, Guang-Can, Zheng, Yu, Sun, Fang-Wen
We theoretically investigate the problem of position detection of an optically levitated Mie particle. The information radiation field (IRF) is proposed and defined to characterize the scattered light carrying complete information about the center-of
Externí odkaz:
http://arxiv.org/abs/2408.15483
Autor:
Tian, Yuan, Zhang, Tianyi
Recent advances in large language models (LLMs) such as Copilot and ChatGPT have transformed software development by automating coding tasks. Despite these advancements, challenges remain in reducing error rates and fully meeting user expectations. O
Externí odkaz:
http://arxiv.org/abs/2408.09121