Scholar
Kaiwen Zhou
Google Scholar ID: FbzTX04AAAAJ
PhD candidate, University of California, Santa Cruz
Citations & Impact
Citations
326
H-index
8
i10-index
7
Publications
15
Co-authors
28
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- First-author paper 'SafeKey' accepted by EMNLP 2025
- First-author paper 'The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1' accepted by IJCNLP-AACL 2025
- Co-first-author paper 'Multimodal Situational Safety' accepted by ICLR 2025; Oral presentation at NeurIPS RBFM Workshop 2024
- Paper 'Navigation as the Attacker Wishes?' accepted by NAACL 2024
- First-author paper 'ESC' accepted by ICML 2023
- Paper 'FedVLN' accepted by ECCV 2022
- Two papers accepted by ACL 2024 ('ViCor' as first author; 'Multipanel VQA' as co-author)
- Awarded UCSC Dissertation-Year Fellowship (2025)
- Invited talk at Microsoft on safety reasoning (2025)
Research Experience
- Research Intern at Microsoft (Summer 2025)
- Research Intern at Honda Research Institute (Spring & Summer 2023)
- Research Intern at Samsung AI Center (Summer 2022)
- Team SlugJARVIS won 3rd place in Amazon Alexa SimBot Challenge (2023)
- Ranked No.1 in Alexa Prize SimBot Public Benchmark Challenge (2022)
