My name is Jiashu Qu, and I am a final-year undergraduate at Chongqing University and the University of Cincinnati.

During my undergraduate studies, I have been fortunate to collaborate with Prof. Yue Zhao and Hongcheng Gao. I greatly benefited from their guidance and mentorship, which has significantly influenced my research interests and direction.

My research interests broadly center on alignment in systems built upon large models, including LLMs, MLLMs, VLA, and Agent-based systems. I am interested in both alignment failures across modalities (e.g. hallucination) and misalignment with human objectives in real-world interactive systems.

📖 Educations

• 2021.09 - 2026.05, Chongqing University & University of Cincinnati
  • Rank: 1 / 97

💻 Experience

• Algorithm Intern, ByteDance Stone
  May 2026 – Aug 2026 (incoming)
  

• Research Intern, The Center of Safe & Trustworthy AI @ Shanghai AI Lab
  May 2025 – Aug 2025
  Mentor: Dongrui Liu

• Research Intern, FORTIS Lab @ University of Southern California
  Dec 2024 – Now
  Mentor: Yue Zhao

📝 Research

• SafeWork-R1: Coevolving Safety and Intelligence under the AI-45 Law
  Shanghai AI Lab et al. (Core Contributor)
  Tech Report
  paper

• The Devil Behind the Mask: An Emergent Safety Vulnerability of Diffusion LLMs
  Z. Wen, J. Qu, D. Liu, Z. Liu, R. Wu, Y. Yang, X. Jin, H. Xu, X. Liu, W. Li, C. Lu
  ICLR 2026
  paper

• Treble Counterfactual VLMs: A Causal Approach to Hallucination
  S. Li, J. Qu, Y. Zhou, Y. Qin, T. Yang, Y. Zhao
  EMNLP 2025
  paper

• Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation
  H. Gao*, J. Qu*, J. Tang*, B. Bi, Y. Liu, H. Chen, L. Liang, L. Su, Q. Huang
  Under review
  paper

🧑‍💻 Academic Service

• Subreviewer, ESORICS 2025

🏆 Honors and Awards

• National Scholarship (Top 1%, twice)
• Meritorious Winner, Mathematical Contest in Modeling (MCM/ICM)

🎯 Miscellaneous

• Fan of FC Bayern Munich · Interested in hip-hop (Asen) · Enjoy playing CSGO

👀 Visitors: · 📊 Page Views: