Yitong Zhang

Yitong Zhang

Beihang University

I’m Yitong Zhang (张奕彤), an undergraduate student at School of Computer Science and Engineering, Beihang University, where I rank 2nd in my college in required courses (2/241). I will be pursuing my Ph.D. at College of AI, Tsinghua University. I am currently working under the supervision of Prof. Jia Li.

My research interests lie in Trustworthy Code Generation, AI for Software Engineering, and Software Engineering for AI. I’m also broadly interested in anything related to AI. I am particularly passionate about improving the reliability and correctness of LLM-generated text and code. If you’re interested in potential collaborations or would like to discuss anything, feel free to contact me via email.

🔥 News

  • 2026.01:  🎉 I was honored with the Outstanding Student of Beijing.
  • 2025.11:  🎉 I was awarded the Shen Yuan Medal, the highest student honor at Beihang University. Among all undergraduates at Beihang, only 10 students received this distinction.
  • 2025.11:  🎉 1 Paper (as first author) accepted by AAAI 2026.
  • 2025.10:  🎉 I was admitted to the College of AI, Tsinghua University for Ph.D. studies (comprehensive evaluation score: 95.8).
  • 2025.10:  🎉 I received the National Scholarship (for the 3rd time).
  • 2024.11:  🎉 I received the Xiaomi Scholarship Special Prize (only 5 undergraduates university-wide).
  • 2024.10:  🎉 My research grant (as Principal Investigator) is approved by Beijing Natural Science Foundation.

📝 Selected Publications

* indicates author with equal contribution and † indicates corresponding author.

  • DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt
    Yitong Zhang, Jia Li, Liyi Cai, Ge Li
    AAAI 2026 Oral
    [paper] [code]

  • DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
    Zherui Li, Zheng Nie, Zhenhong Zhou, Yufei Guo, Yue Liu, Yitong Zhang, Yu Cheng, Qingsong Wen, Kun Wang, Jiaheng Zhang
    ICLR 2026
    NeurIPS 2025 Workshop
    [paper] [code]

  • Lookahead-then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars
    Yitong Zhang, Yongmin Li, Yuetong Liu, Jia Li, Xiaoran Jia, Zherui Li, Ge Li
    Preprint
    [paper] [code]

  • Beyond Autoregression: An Empirical Study of Diffusion Large Language Models for Code Generation
    Chengze Li*, Yitong Zhang*, Jia Li, Liyi Cai, Ge Li
    Preprint
    [paper] [code]

  • Environmental Injection Attacks against GUI Agents in Realistic Dynamic Environments
    Yitong Zhang, Ximo Li, Liyi Cai, Jia Li
    Preprint
    [paper] [code]

  • AI-Driven Self-Evolving Software: A Promising Path Toward Software Automation
    Liyi Cai*, Yijie Ren*, Yitong Zhang*, Jia Li
    Preprint
    [paper] [code]

  • DiffuTester: Accelerating Unit Test Generation for Diffusion LLMs via Mining Structural Pattern
    Lekang Yang, Yuetong Liu, Yitong Zhang, Jia Li
    Preprint
    [paper] [code]

  • Visual Adversarial Attack on Vision-Language Models for Autonomous Driving
    Tianyuan Zhang, Lu Wang, Xinwei Zhang, Yitong Zhang, Boyi Jia, Siyuan Liang, Shengshan Hu, Aishan Liu, Xianglong Liu
    Preprint
    [paper]

  • Enhancing the Transferability of Adversarial Attacks with Stealth Preservation
    Xinwei Zhang, Tianyuan Zhang, Yitong Zhang, Shuangcheng Liu
    CVPR 2024 Workshop
    [paper]

  • Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment
    Kun Wang, Zherui Li, Zhenhong Zhou, Yitong Zhang, Yan Mi, Kun Yang, Yiming Zhang, Junhao Dong, Zhongxiang Sun, Qiankun Li, Yang Liu
    Preprint
    [paper] [code]

  • Improving Sampling for Masked Diffusion Models via Information Gain
    Kaisen Yang, Jayden Teoh, Kaicheng Yang, Yitong Zhang, Alex Lamb
    Preprint
    [paper] [code]

  • PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
    Xiting Liu, Yuetong Liu, Yitong Zhang, Jia Li, Shi-Min Hu
    Preprint
    [paper] [code]

  • What Papers Don’t Tell You: Recovering Tacit Knowledge for Automated Paper Reproduction
    Lehui Li, Ruining Wang, Haochen Song, Yaoxin Mao, Tong Zhang, Yuyao Wang, Jiayi Fan, Yitong Zhang, Jieping Ye, Chengqi Zhang, Yongshun Gong
    Preprint
    [paper]

✨ Grants

  • Large Model Driven End-to-End Autonomous Driving Model Adversarial Attacks
    Principal Investigator, Beijing Natural Science Foundation (Grant No. QY24136)
    2024.10 - 2026.09

🎖 Honors and Awards

  • Shen Yuan Medal (top 0.1%), the highest honor scholarship of Beihang University, 2025
  • Xiaomi Scholarship Special Prize (only 5 undergraduates university-wide), 2024
  • China National Scholarship (3rd time), 2025
  • China National Scholarship (2nd time), 2024
  • China National Scholarship, 2023
  • First prize, Chinese Mathematics Competitions for Undergraduates (Beijing Division), 2023
  • Outstanding Student of Beijing, 2026
  • Outstanding Student of Shandong, 2022

📖 Educations

  • 2026.09 (expected), Ph.D. Student, College of AI, Tsinghua University
  • 2022.09 - 2026.06 (expected), Undergraduate Student, School of Computer Science and Engineering, Beihang University
  • 2019.09 - 2022.06, High School Student, Shandong Taian No.1 Senior High School

💼 Interns

  • 2025.12 - present, Intern at Fitten

📚 Services

  • Reviewer: AAAI 2026

👩🏻‍🏫 Teaching

  • Teaching Assistant, Discrete Mathematics, Beihang University, Spring 2025
  • Teaching Assistant, Computer Organization, Beihang University, Fall 2024
  • Senior Teaching Assistant, Data Structures and Programming, Beihang University, Spring 2024

🔗 Links