影响力指数

-/100

发表论文2 篇

平均评分2.5

年均产出2.0 篇/年

Samuel Simko

Researcher@ETHZ - ETH Zurich·瑞士·OpenReview

研究方向

AI safety · Deep learning

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering

ICLR 2026Rejected

Accidental Vulnerability: Factors in Fine-Tuning that Shift Model Safeguards

ICLR 2026Rejected

合作者 (10)

Punya Syon Pandey

Samanvay Vajpayee

Sirisha Rambhatla