Maria Angelica Martinez

Researcher, School of Statistics, University of the Philippines

Joined

September 2024

Names

Maria Angelica Martinez (Preferred)

Emails

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Researcher

School of Statistics, University of the Philippines (up.edu.ph)

2011 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

AI Safety

2024 – Present

Publications

Better Attacks for Better Monitors: Semi-Automated Red-Teaming for Agent Monitoring
Monika Jotautaitė, Maria Angelica Martinez, Tyler Tracy, Ollie Matthews
- ICLR 2026 AIWILD
- Readers: Everyone
Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack
Leo McKee-Reid, Christoph Sträter, Maria Angelica Martinez, Joe Needham, Mikita Balesni
- SafeGenAi Poster
- Readers: Everyone
Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack
Leo McKee-Reid, Christoph Sträter, Maria Angelica Martinez, Joe Needham, Mikita Balesni
- Submitted to ICLR 2025
- Readers: Everyone
Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack
Leo McKee-Reid, Christoph Sträter, Maria Angelica Martinez, Joe Needham, Mikita Balesni
- SoLaR Poster
- Readers: Everyone

Co-Authors