Scholar
Junxiao Yang
Google Scholar ID: 8Zu6HocAAAAJ
Tsinghua University
Citations & Impact
Citations
278
H-index
6
i10-index
3
Publications
11
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- Paper accepted at ACL 2025 Main Conference: 'Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints' (first author)
- ACL 2024 Long Paper: 'Defending large language models against jailbreaking attacks through goal prioritization' (co-first author)
- Multiple preprints on LLM safety, knowledge boundaries, fine-tuning data leakage, and safety evaluation frameworks
- Developed AISafetyLab: a comprehensive framework for AI safety evaluation and improvement
- Excellent Graduate, Tsinghua University, 2025
- 3rd Prize, Global Challenge for Safe and Secure LLMs (Track 1)
- Academic Excellence in Research Award, Tsinghua University (2023.09–2024.09)
- Meritorious Winner, Mathematical Contest In Modeling, 2023
- Comprehensive Scholarship, Tsinghua University (2021–2023, two consecutive years)
