Rom Himelstein
3 papers · 2025–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
Top co-authors
Keywords
safety alignment
(2)
model uncertainty
(1)
adversarial attack
(1)
language model
(1)
latent space
(1)
vision-language model
(1)
jailbreak attack
(1)
hallucination detection
(1)
fairness evaluation
(1)
linguistic feature
(1)
activation steering
(1)
activation space
(1)
large language model
(1)
refusal suppression
(1)
bias detection
(1)
next-token probabilities
(1)