Get started
Author

Lukas Fluri

Observed name: Fluri, Lukas
Institution: ETH Zurich
Observed institution: ETH Zurich
OpenAlex ID: A5092207591
Evaluating Superhuman Models with Consistency Checks
2024 · Lukas Fluri, Daniel Paleka, et al. · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · 40
PDF
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
2024 · Fluri, Lukas, Lang, Leon, et al. · arXiv (Cornell University) · 8
PDF
CryptanalysisBench: Can LLMs do Cryptanalysis?
2026 · Fluri, Lukas, Shafran, Avital, et al. · arXiv (Cornell University) · 1
PDF
Position: Anthropomorphic Misalignment Research Needs Stronger Evidence
2026 · Gupta, Vansh, Nutter, Peter, et al. · arXiv (Cornell University) · 1
PDF
Not All Misalignment Is Alike: A Decomposed Benchmark for Emergent Misalignment
2026 · Domingues, Afonso, Akhtar, Mubashara, et al. · arXiv (Cornell University)
PDF
Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment
2026 · Liu, Shunchang, Fluri, Lukas, et al. · arXiv (Cornell University)
PDF
Works count: 6
Citation count: 50
H-index: 2
I10-index: 1
Year
Topic
Type