Yaniv Nemcovsky
4 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
🗺️
Taxonomy Completionist
(10)
Top co-authors
Research topics
Keywords
safety alignment
(2)
large language model
(2)
bias detection
(1)
machine unlearning
(1)
adversarial attack
(1)
language model
(1)
foundation model
(1)
latent space
(1)
jailbreak attack
(1)
fairness evaluation
(1)
linear operator
(1)
activation steering
(1)
activation space
(1)
refusal suppression
(1)
input loss landscape
(1)
prompt semantic space
(1)
residual memorization
(1)
memorization state
(1)
representation learning
(1)
neighborhood dynamics
(1)
Papers
REMIND: Memorization and Unlearning in LLMs Through the Lens of Input Loss Landscapes
ACL 2026
Silenced Biases: The Dark Side LLMs Learned to Refuse
AAAI 2026
Jailbreak Attack Initializations as Extractors of Compliance Directions
EMNLP 2025
Representing LLMs in Prompt Semantic Task Space
EMNLP 2025