Zobrazeno 1 - 10
of 454
pro vyhledávání: '"Li, Zongjie"'
Large code models (LCMs), pre-trained on vast code corpora, have demonstrated remarkable performance across a wide array of code-related tasks. Supervised fine-tuning (SFT) plays a vital role in aligning these models with specific requirements and en
Externí odkaz:
http://arxiv.org/abs/2408.08343
Autor:
Wang, Xunguang, Wu, Daoyuan, Ji, Zhenlan, Li, Zongjie, Ma, Pingchuan, Wang, Shuai, Li, Yingjiu, Liu, Yang, Liu, Ning, Rahmel, Juergen
Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the recent indir
Externí odkaz:
http://arxiv.org/abs/2406.05498
The rapid advancement of deep learning has led to the development of Large Language Models (LLMs). In the field of vulnerability repair, previous research has leveraged rule-based fixing, pre-trained models, and LLM's prompt engineering. However, exi
Externí odkaz:
http://arxiv.org/abs/2405.04994
Autor:
Wang, Chaozheng, Li, Zongjie, Gao, Cuiyun, Wang, Wenxuan, Peng, Ting, Huang, Hailiang, Deng, Yuetang, Wang, Shuai, Lyu, Michael R.
Code generation aims to synthesize code and fulfill functional requirements based on natural language (NL) specifications, which can greatly improve development efficiency. In the era of large language models (LLMs), large code models (LCMs) have bee
Externí odkaz:
http://arxiv.org/abs/2404.19368
Agents based on large language models (LLMs) have demonstrated effectiveness in solving a wide range of tasks by integrating LLMs with key modules such as planning, memory, and tool usage. Increasingly, customers are adopting LLM agents across a vari
Externí odkaz:
http://arxiv.org/abs/2404.17833
Visual deep learning (VDL) systems have shown significant success in real-world applications like image recognition, object detection, and autonomous driving. To evaluate the reliability of VDL, a mainstream approach is software testing, which requir
Externí odkaz:
http://arxiv.org/abs/2404.13945
Autor:
Li, Zongjie, Qiu, Wenying, Ma, Pingchuan, Li, Yichen, Li, You, He, Sijia, Jiang, Baozheng, Wang, Shuai, Gu, Weixi
Recent years have witnessed the rapid development of large language models (LLMs) in various domains. To better serve the large number of Chinese users, many commercial vendors in China have adopted localization strategies, training and providing loc
Externí odkaz:
http://arxiv.org/abs/2402.01723
Autor:
Li, Zongjie, Wang, Chaozheng, Liu, Chaowei, Ma, Pingchuan, Wu, Daoyuan, Wang, Shuai, Gao, Cuiyun
With recent advancements in Large Multimodal Models (LMMs) across various domains, a novel prompting method called visual referring prompting has emerged, showing significant potential in enhancing human-computer interaction within multimodal systems
Externí odkaz:
http://arxiv.org/abs/2312.04087
Large vision-language models (LVLMs) have demonstrated their incredible capability in image understanding and response generation. However, this rich visual interaction also makes LVLMs vulnerable to adversarial examples. In this paper, we formulate
Externí odkaz:
http://arxiv.org/abs/2312.01886
Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach
While code generation has been widely used in various software development scenarios, the quality of the generated code is not guaranteed. This has been a particular concern in the era of large language models (LLMs)- based code generation, where LLM
Externí odkaz:
http://arxiv.org/abs/2310.06680