Scholar
Vinu Sankar Sadasivan
Google Scholar ID: y1IKIw0AAAAJ
PhD Candidate at University of Maryland, College Park
Citations & Impact
Citations
955
H-index
7
i10-index
7
Publications
16
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- Paper: 'IConMark: Robust Interpretable Concept-Based Watermark For AI Images', GenAI Watermarking, ICLR 2025
- Paper: 'LLM-Check: Investigating Detection of Hallucinations in Large Language Models', NeurIPS 2024
- Paper: 'BEAST', ICML 2024
- Recipient of the Kulkarni Fellowship 2023
- Invited talks at various academic conferences and companies
- Reviewer for ICLR 2023, NeurIPS 2022, and other conferences
Background
- AI Research Scientist, currently working with the Llama safety team at Meta. Main research interest is AI safety.
Miscellany
- Personal interests not mentioned
