Scholar
Zheyuan Liu
Google Scholar ID: NLA-nSUAAAAJ
University of Notre Dame
Citations & Impact
Citations
587
H-index
12
i10-index
14
Publications
20
Co-authors
17
list available
Publications
Resume (English only)
Academic Achievements
- Two papers accepted by EMNLP main in 2025; two first-author papers accepted by ACL main in 2025; one paper accepted by NAACL main and one by NAACL findings in 2025; new benchmark paper about MLLM Unlearning released in October 2024; two papers accepted by EMNLP main in September 2024; new survey paper about Generative AI Machine Unlearning released in July 2024; one paper accepted to ACL 2024 in May 2024; will join Amazon as an Applied Scientist Intern in summer 2024.
Research Experience
- Published multiple papers in top conferences, focusing on areas such as model merging, neuron pruning, knowledge disentanglement, and privacy protection.
Education
- Currently a third-year CS PhD student at the University of Notre Dame, advised by Prof. Meng Jiang; received B.S. in Computer Science and Applied Math from Brandeis University.
Background
- Research interests include GenAI (e.g., MLLM/LLM) Safety, AI Privacy, Trustworthy AI, Agentic Safety, and Multi-Agent Collaboration. Currently exploring Agentic Safety and Multi-agent collaboration.
Miscellany
- Active blog writer on Red Notes (小红书); contact information includes Email, CV, Google Scholar, Semantic Scholar, X (Twitter), Github, LinkedIn, and Red Notes (小红书).
