8 citations · 9 across the 13 of their papers we have counts for
13 papers
Looks Right, Works Right: A Project-Level Benchmark for Multi-Screen Mobile App Generation
Fan Wu, Cuiyun Gao, Yiming Huang +3
Recent multimodal large language models can convert visual designs directly into executable code, but real mobile products require multiple screenshots to become a buildable codeba…
Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages
Fan Wu, Lishuai Dong, Cuiyun Gao +4
Recent advancements in multimodal large language models (MLLMs) have achieved remarkable progress in multimodal reasoning and code generation, catalyzing a new paradigm for front-e…
Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning
Zhanyue Qin, Jia Feng, Yibo Lyu +4
Code reasoning refers to the task of predicting the output of a program given its source code and specific inputs. It can measure the reasoning capability of large language models…
Benchmarking Code LLM-as-a-Judge via Constrained Perturbation and Calibration
Ruiqi Wang, Xinchen Wang, Cuiyun Gao +3
Code from LLM-assisted development may contain defects like API hallucinations, motivating the development of code evaluation metrics to assess such code before deployment. As conv…
A Systematic Literature Review of Code Hallucinations in LLMs: Characterization, Mitigation Methods, Challenges, and Future Directions for Reliable AI
Cuiyun Gao, Guodong Fan, Chun Yong Chong +5
Model hallucination is one of the most critical challenges faced by Large Language Models (LLMs), especially in high-stakes code intelligence tasks. As LLMs become increasingly int…
An Empirical Study of Knowledge Distillation for Code Understanding Tasks
Ruiqi Wang, Zezhou Yang, Cuiyun Gao +2
Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due t…
MLLM-Based UI2Code Automation Guided by UI Layout Information
Fan Wu, Cuiyun Gao, Shuqing Li +2
Converting user interfaces into code (UI2Code) is a crucial step in website development, which is time-consuming and labor-intensive. The automation of UI2Code is essential to stre…
EvalSVA: Multi-Agent Evaluators for Next-Gen Software Vulnerability Assessment
Xin-Cheng Wen, Jiaxin Ye, Cuiyun Gao +2
Software Vulnerability (SV) assessment is a crucial process of determining different aspects of SVs (e.g., attack vectors and scope) for developers to effectively prioritize effort…
Repository-Level Graph Representation Learning for Enhanced Security Patch Detection
Xin-Cheng Wen, Zirui Lin, Cuiyun Gao +3
Software vendors often silently release security patches without providing sufficient advisories (e.g., Common Vulnerabilities and Exposures) or delayed updates via resources (e.g.…
Bridge and Hint: Extending Pre-trained Language Models for Long-Range Code
Yujia Chen, Cuiyun Gao, Zezhou Yang +2
In the field of code intelligence, effectively modeling long-range code poses a significant challenge. Existing pre-trained language models (PLMs) such as UniXcoder have achieved r…
ReposVul: A Repository-Level High-Quality Vulnerability Dataset
Xinchen Wang, Ruida Hu, Cuiyun Gao +3
Open-Source Software (OSS) vulnerabilities bring great challenges to the software security and pose potential risks to our society. Enormous efforts have been devoted into automate…
APIGen: Generative API Method Recommendation
Yujia Chen, Cuiyun Gao, Muyijie Zhu +3
Automatic API method recommendation is an essential task of code intelligence, which aims to suggest suitable APIs for programming queries. Existing approaches can be categorized i…
Game Rewards Vulnerabilities: Software Vulnerability Detection with Zero-Sum Game and Prototype Learning
Xin-Cheng Wen, Cuiyun Gao, Xinchen Wang +3
Recent years have witnessed a growing focus on automated software vulnerability detection. Notably, deep learning (DL)-based methods, which employ source code for the implicit acqu…