Scholar
Haoyu Wang
Google Scholar ID: l_QMtXYAAAAJ
Tsinghua University
Citations & Impact
Citations
92
H-index
5
i10-index
4
Publications
9
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- - 2025 NeurIPS Paper: 'Lifelong Safety Alignment for Language Models'
- - 2025 ICML Paper: 'Safety Reasoning with Guidelines'
- - 2025 ICML Paper: 'Mastering Massive Multi-Task Reinforcement Learning via MoE Decision Transformer'
- - 2024 ICML MHFAIA Workshop Paper: 'Step-on-feet Tuning: Scaling Self-alignment of LLMs via Bootstrapping'
- - TMLR Journal Paper: 'Are large language models really robust to word-level perturbations?'
- - 2023 NeurIPS Paper: 'Learning better with less: Effective augmentation for sample-efficient visual reinforcement learning'
- - Honors and Awards: XJTU Excellent Student Scholarship, Tsinghua Comprehensive Excellence Scholarship, Tsinghua Big Data Practice Scholarship
Research Experience
- - 2023.09 - 2024.10, Internship at Tencent, Advised by: Peilin Zhao
- - 2024.10 - 2025.07, Associate Member at Sea AI Lab, Collaborated with: Tianyu Pang, Li Shen, Dacheng Tao
Education
- - 2022.09 - 2025.06, Master, Tsinghua University, Advisor: Prof. Xueqian Wang
- - 2018.09 - 2022.06, Undergraduate, Xi’an Jiaotong University
Background
- Research Interest: AI alignment, especially ensuring the safety of LLM and using synthetic data to help LLM self-improve. Professional Field: Electrical Engineering and Automation.
Miscellany
- Personal interests not mentioned
