Dong HUANG

Dong HUANG

Rm 414, Chow Yei Ching Building, Pok Fu Lam Road, dhuang@cs.hku.hk

About me

I am currently a Research Fellow at the Institute of Data Science, National University of Singapore, under the supervision of Prof. See-Kiong Ng, and I also closely collaborated with Dr. Jie M.Zhang and Dr. Zhijiang Guo. Before that, I obtained my PhD degree in the Computer Science Department at the University of Hong Kong, under the supervision of Prof. Heming Cui. I earned a Bachelor degree from Huazhong University of Science and Technology with honors. You can find my CV here: Dong’s CV

Please do not hesitate to contact me if you have any questions regarding my work or if you are interested in discussing research topics!

News

  • Aug 21, 2025: Our paper "Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward" was accepted by EMNLP-Findings 2025.
  • June 20, 2025: Our paper "Measuring the Influence of Incorrect Code on Test Generation" was accepted by ICSE 2026 (60/660, 9.1%).
  • May 1, 2025: Our paper "EffiCoder (SwiftCoder): Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning" was accepted by ICML 2025.
  • Feb 26, 2025: Our paper "Bias Testing and Mitigation in LLM-based Code Generation" was accepted by TOSEM.
  • Sep 26, 2024: Our paper "SOAP (EffiLearner): Enhancing Efficiency of generated Code via Self-Optimization" was accepted by NeurIPS.
  • Sep 26, 2024: Our paper "EffiBench: Benchmarking the Efficiency of Automatically Generated Code" was accepted by NeurIPS.
  • July 27, 2024: Our paper "Themis: Automatic and Efficient Deep Learning System Testing with Strong Fault Detection Capability" was accepted by ISSRE.
  • May 9, 2024: Our paper "Neuron Sensitivity Guided Test Case Selection" was accepted by TOSEM.
  • Jan 29, 2024: Our paper "AGRNav: Efficient and Energy-Saving Autonomous Navigation for Air-Ground Robots in Occlusion-Prone Environments" was accepted by ICRA'24.
  • Jan 16, 2024: Our paper "Adversarial Feature Map Pruning for Backdoor" was accepted by ICLR'24.
  • July 18, 2023: One paper "Towards building more robust models with frequency bias" was accepted by ICCV'23.

Selected Publications (✉ refers to the corresponding author)

Preprint

  • Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
    Mingzhe Du, Luu Tuan Tuan, Yue Liu, Yuhao Qing, Dong Huang✝, Xinyi He, Qian Liu, Zejun Ma, See-kiong Ng
    arXiv preprint arXiv:2505.23387

  • EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code
    Yuhao Qing, Boyu Zhu, Mingzhe Du, Zhijiang Guo, Terry Yue Zhuo, Qianru Zhang, Jie M. Zhang, Heming Cui, Siu-Ming Yiu, Dong Huang✝, See-Kiong Ng, Luu Anh Tuan
    arXiv preprint arXiv:2505.13004

  • DS-Bench: A Realistic Benchmark for Data Science Code Generation
    Shuyin Ouyang, Dong Huang, Jingwen Guo, Zeyu Sun, Qihao Zhu, Jie M. Zhang
    arXiv preprint arXiv:2505.15621

  • Agentcoder: Multi-agent-based code generation with iterative testing and optimisation
    Dong HUANG, Qingwen Bu, Jie M Zhang, Michael Luck, Heming Cui
    arXiv preprint arXiv:2312.13010

Conference

  • [EMNLP-Findings’25] Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward
    Han Weng, Puzhen Wu, Cui Longjie, Yi Zhan, Boyi Liu, Yuanfeng Song, Dun Zeng, Yingxiang Yang, Qianru Zhang, Dong Huang✉, Xiaoming Yin, Yang Sun✉, Xing Chen arXiv preprint arXiv:2409.09464

  • [ICSE’26] Rethinking the Influence of Source Code on Test Case Generation
    Dong Huang, Jie M. Zhang, Mark Harman, Mingzhe Du, Heming Cui arXiv preprint arXiv:2409.09464

  • [ACL’25 Demo] CodeArena: A Collective Evaluation Platform for LLM Code Generation
    Mingzhe Du, Anh Tuan Luu, Bin Ji, Xiaobao Wu, Dong Huang, Terry Yue Zhuo, Qian Liu, See-Kiong Ng
    arXiv preprint arXiv:2503.01295

  • [ICML’25] EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning
    Dong HUANG, Guangtao Zeng, Jianbo Dai, Meng Luo, Han Weng, Yuhao QING, Heming Cui, Zhijiang Guo, Jie Zhang
    arXiv preprint arXiv:2410.10209

  • [ICASSP’25] Rethinking adversarial attacks in reinforcement learning from policy distribution perspective
    Tianyang Duan, Zongyuan Zhang, Zheng Lin, Yue Gao, Ling Xiong, Yong Cui, Hongbin Liang, Xianhao Chen, Heming Cui, Dong Huang✉ https://ieeexplore.ieee.org/document/10890540
    Corresponding Author

  • [NeurIPS’24] EffiLearner: Enhancing Efficiency of generated Code via Self-Optimization
    Dong HUANG, Jianbo Dai, Han Weng, Puzhen Wu, Yuhao Qing, Jie M. Zhang, Heming Cui, and Zhijiang Guo
    arXiv preprint arXiv:2405.15189

  • [NeurIPS’24] EffiBench: Benchmarking the Efficiency of Automatically Generated Code
    Dong HUANG, Yuhao Qing, Weiyi Shang, Heming Cui, Jie M.Zhang
    arXiv preprint arXiv:2402.02037

  • [ISSRE’24] Themis: Automatic and Efficient Deep Learning System Testing with Strong Fault Detection Capability
    Dong HUANG, Li Tsz On, Xiaofei Xie, Heming Cui
    arXiv preprint arXiv:2405.09314

  • [ICLR’24] Adversarial Feature Map Pruning for Backdoor
    Dong HUANG, Qingwen Bu
    In: The Twelfth International Conference on Learning Representations, Messe Wien Exhibition and Congress Center, Vienna Austria May 7th, 2024 to May 11th, 2024

  • [ICCV’23] Towards building more robust models with frequency bias
    Qingwen Bu, Dong HUANG✉, Heming Cui
    In: Proceedings of the IEEE/CVF International Conference on Computer Vision, PARIS, October 2 - 6, 2023
    Corresponding Author

Journal

  • [TOSEM’25] Bias assessment and mitigation in llm-based code generation
    Dong HUANG, Jie M. Zhang, Qingwen Bu, Xiaofei Xie, Junjie Chen, Heming Cui
    arXiv preprint arXiv:2309.14345

  • [TOSEM’24] Neuron Sensitivity Guided Test Case Selection
    Dong HUANG, Qingwen Bu, Yichao Fu, Yuhao Qing, Xiaofei Xie, Junjie Chen, Heming Cui
    In: ACM Transactions on Software Engineering and Methodology, 2024

Work Experience

  • Research Intern @: HUAWEI Theory Lab, Hong Kong (2022), working with Qintao Hu and Sen Wang
  • Research Intern @: HUAWEI Noah's Ark Lab, Shenzhen (2024), working with Jianbo Dai and Zhijiang Guo

Services

  • Reviewers: ICML (2025), ICLR (2025), NeurIPS (2024), NeurIPS Dataset and Benchmark Track (2024), ACL ARR (e.g., NAACL, EMNLP, ACL) (2024)

Research Mentoring

I am fortunate to be working with the following talented students and interns:

  • Qingwen Bu: Undergrad at HUST, to PhD at SJTU-PJLab
  • Junming Wang: Mphil at HKU, to Horizon Robotics
  • Zhiguang Han: Undergrad at NTU
  • Weng Han: Master at BUPT
  • Puzhen Wu: Undergrad at UCD

Media Coverage

Artificial Intelligence Index Report 2024 - Stanford University, The latest on global AI development, Build Your Own Devin!

Teaching

  • COMP7506 A: Smart phone apps development, Spring 2024
  • COMP7506 B: Smart phone apps development, Spring 2024

Education

  • The University of Hong Kong: 2021-2025
  • Huazhong Univeristy of Science and Technology: 2017-2021