Scholar
Diogo Cruz
Google Scholar ID: ybn2AhcAAAAJ
PhD Student, Instituto Superior Técnico
quantum computing
quantum information
quantum algorithms
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
199
H-index
5
i10-index
2
Publications
12
Co-authors
4
Publications
7 items
Efficient Safety Benchmarking via Item Response Theory
arXiv.org · 2026
Cited
0
Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals
2026
Cited
0
Asymmetric Goal Drift in Coding Agents Under Value Conflict
2026
Cited
0
When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents
2025
Cited
0
Multi-Turn Jailbreaks Are Simpler Than They Seem
2025
Cited
0
Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods
2025
Cited
0
Understanding the learned look-ahead behavior of chess neural networks
2025
Cited
0
