Mantas Mazeika
Source-listed: Research Scientist · Center for AI Safety
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Measuring Massive Multitask Language UnderstandingSaved credit: Contributor · 2021Explore people connected to this work →
- PixMix: Dreamlike Pictures Comprehensively Improve Safety MeasuresSaved credit: Contributor · 2022Explore people connected to this work →
- An Overview of Catastrophic AI RisksSaved credit: Contributor · 2023Explore people connected to this work →
- The WMDP Benchmark: Measuring and Reducing Malicious Use With UnlearningSaved credit: Contributor · 2024Explore people connected to this work →
- Tamper-Resistant Safeguards for Open-Weight LLMsSaved credit: Contributor · 2025Explore people connected to this work →