Dr. Jialun, CAO (Bella)

Dr. Jialun, CAO (Bella)

Research Assistant Professor

Hong Kong University of Science and Technology

Biography

Jialun CAO received her PhD degree from the Department of Computer Science and Engineering at HKUST, under the supervision of Prof. S.C. Cheung. Her research interests lie in the intersection of Software Engineering (SE) and Artificial Intelligence (AI), with an emphasis on SE4AI and AI4SE, and trustworthy AI. Currently, she is also exploring the large language model 4 SE (LLM4SE). Collaborations and discussions are welcomed!

Download my resumé.

Interests
  • Deep Learning Testing
  • Trustworthy AI
  • LLM4SE
  • AI4Formal Verification
Education

  • PhD in Computer Science, 2024

    Hong Kong University of Science and Technology

  • MEng in Computer Science, 2019

    Chinese Academy of Sciences, Institute of Software

  • BEng in Digital Media Technology, 2016

    Shandong University

Selected Publications

2024

  arXiv    Can AI Beat Undergraduates in Entry-level Java Assignments? Benchmarking Large Language Models on JavaBench. [Paper] [Leaderboard][Benchmark]

Jialun Cao (Co-1st), Zhiyong Chen (Co-1st), Jiarong Wu, Shing-chi Cheung, Chang Xu

  arXiv    Concerned with Data Contamination? Assessing Countermeasures in Code Language Model. [Paper]

Jialun Cao, Wuqi Zhang, Shing-Chi Cheung

  CAV    Enchanting Program Specification Synthesis by Large Language Models using Static Analysis and Program Verification. [Paper]

Cheng Wen, Jialun Cao (Corresponding), Jie Su, Zhiwu Xu, Shengchao Qin (Corresponding), Mengda He, Haokun Li, Shing-Chi Cheung, Cong Tian

  arXiv    DLLens: Testing Deep Learning Libraries via LLM-aided Synthesis. [Paper]

Meiziniu Li, Dongze Li, Jianmeng Liu, Jialun Cao, Yongqiang Tian, Shing-Chi Cheung

  TASE    Fuzzing for Stateful Protocol Implementations: Are We There Yet?

Kunpeng Jian, Yanyan Zou, Yeting Li, Jialun Cao, Menghao Li, Jian Sun, Jingyi Shi and Wei Huo

2023

  FSE    Testing Coreference Resolution Systems without Labeled Test Sets. [Paper] [Code]

Jialun Cao, Yaojie Lu, Ming Wen, Shing-Chi Cheung

  FSE    Understanding the Bug Characteristics and Fix Strategies of Federated Learning Systems. [Paper]

Xiaohu Du, Xiao Chen, Jialun Cao, Ming Wen, Shing-Chi Cheung, Hai Jin

  TOSEM    COMET: Coverage-guided Model Generation For Deep Learning Library Testing. [Paper]

Meiziniu Li, Jialun Cao, Yongqiang Tian, Tsz On Li, Ming Wen, Shing-Chi Cheung

  arXiv    A study on prompt design, advantages and limitations of chatgpt for deep learning program repair. [Paper]

Jialun Cao, Meiziniu Li, Ming Wen, Shing-chi Cheung

2022

  TOSEM    SemMT: A Semantic-Based Testing Approach for Machine Translation Systems. [Paper] [Code]

Jialun Cao, Meiziniu Li, Yeting Li, Ming Wen, Shing-chi Cheung

  ICSE    DeepFD: Automated Fault Diagnosis and Localization for Deep Learning Programs. [Paper] [Code]

Jialun Cao, Meiziniu Li, Xiao Chen, Ming Wen, Yongqiang Tian, Bo Wu, Shing-chi Cheung

  Usenix Security    RegexScalpel: Regular Expression Denial of Service (ReDoS) Defense by Localize-and-Fix. [Paper]

Yeting Li, Yecheng Sun, Zhiwu Xu, Jialun Cao, Yuekang Li, Rongchen Li, Haiming Chen, Shing-Chi Cheung, Yang Liu, Yang Xiao

2021

  Usenix Security    ReDoSHunter: A Combined Static and Dynamic Approach for Regular Expression DoS Detection. [Paper]

Yeting Li, Zixuan Chen, Jialun Cao, Zhiwu Xu, Qiancheng Peng, Haiming Chen, Liyuan Chen, Shing-Chi Cheung

  ICSE    TRANSREGEX: Multi-modal Regular Expression Synthesis by Generate-and-Repair. [Paper]

Yeting Li, Shuaimin Li, Zhiwu Xu, Jialun Cao, Zixuan Chen, Yun Hu, Haiming Chen, Shing-Chi Cheung

2020

See all
  ICDE    FlashSchema: Achieving High Quality XML Schemas with Powerful Inference Algorithms and Large-scale Schema Data. [Paper]

Yeting Li, Jialun Cao, Haiming Chen, Tingjian Ge, Zhiwu Xu, Qiancheng Peng

  ASE    FlashRegex: Deducing Anti-ReDoS Regexes from Examples. [Paper]

Yeting Li, Zhiwu Xu, Jialun Cao, Haiming Chen, Tingjian Ge, Shing-Chi Cheung

2019

See all
  ICCD    A Learning-Based Framework for Automatic Parameterized Verification. [Paper]

Yongjian Li Jialun Cao (1st Stuent Author), Jun Pang

  DASFAA    Learning k-Occurrence Regular Expressions with Interleaving. [Paper]

Yeting Li, Xiaolan Zhang, Jialun Cao, Haiming Chen, Chong Gao

2018

  ASE    L-CMP: an automatic learning-based parameterized verification tool. [Paper] [Code] [Video]

Jialun Cao, Yongjian Li, Jun Pang

See all publications at DBLP or Google Scholar.

Academic ­Services

Program Committee

  • ICSE 2024 research track
  • APSEC 2024 technical track
  • ISSRE 2024 research track
  • Internetware 2024 research track
  • TASE 2024 research track (Sub-reviewer)
  • AIWare 2024
  • FORGE 2024
  • AutoMates@IJCAI 2024
  • ICMR 2024

Reviewer

  • TOSEM (ACM Transactions on Software Engineering and Methodology

  • TSE (IEEE Transactions on Software Engineering)

  • EMSE (Empirical Software Engineering)

  • TKDD (ACM Transactions on Knowledge Discovery from Data)

  • Journal of Software (软件学报)

  • TMC (IEEE Transactions on Mobile Computing)

Recent & Upcoming Talks

基于大模型的需求描述到形式化规约生成初探 (A Preliminary Study on the Generation of Formal Specifications from Requirements Description Based on Large Language Model）
2024 CCF形式化方法专委会战略研讨会—形式化方法与人工智能的交叉融合：机遇与挑战 (Cross-integration of formal methods and artificial intelligence - opportunities and challenges)
May 5, 5050 9:00 AM — 5:00 PM
基于大模型的需求描述到形式化规约生成初探 (A Preliminary Study on the Generation of Formal Specifications from Requirements Description Based on Large Language Model）
Understanding the Bug Characteristics and Fix Strategies of Federated Learning Systems
ESEC/FSE 23 Presentation
Dec 7, 7070 11:30 AM — 11:45 AM
Understanding the Bug Characteristics and Fix Strategies of Federated Learning Systems
Testing Coreference Resolution Systems without Labeled Test Sets
ESEC/FSE 23 Presentation
Dec 5, 5050 11:45 AM — 12:00 PM
Testing Coreference Resolution Systems without Labeled Test Sets
步履不停，折腾不止 -- 从艺术生“上岸”成工科博士的“折腾”史
软件工程女性学者论坛 (Forum for Women Scholars in Software Engineering)
Dec 2, 2020 10:00 AM — Jun 14, 14140 11:00 AM
步履不停，折腾不止 -- 从艺术生“上岸”成工科博士的“折腾”史
关于大语言模型时代的的代码数据泄漏问题的实证研究
AIGC下的软件工程新范式论坛
Dec 1, 1010 3:30 PM — 4:00 PM
关于大语言模型时代的的代码数据泄漏问题的实证研究
See all events

Contact