← People

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
  1. Measuring Massive Multitask Language UnderstandingSaved credit: Contributor · 2021Explore people connected to this work →
  2. PixMix: Dreamlike Pictures Comprehensively Improve Safety MeasuresSaved credit: Contributor · 2022Explore people connected to this work →
  3. An Overview of Catastrophic AI RisksSaved credit: Contributor · 2023Explore people connected to this work →
  4. The WMDP Benchmark: Measuring and Reducing Malicious Use With UnlearningSaved credit: Contributor · 2024Explore people connected to this work →
  5. Tamper-Resistant Safeguards for Open-Weight LLMsSaved credit: Contributor · 2025Explore people connected to this work →