Amit Levi
5 papers · 2021–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (4) π Cross-Pollinator (13) π Academic Marathon (5) πΊοΈ Taxonomy Completionist (10)
π§
Keyword Pioneer
Conferences
AAAI (1)
COLT (1)
EMNLP (1)
ICLR (1)
JMLR (1)
Top co-authors
Keywords
safety alignment
(2)
attention mechanism
(1)
bias detection
(1)
distribution testing
(1)
stochastic block model
(1)
adversarial attack
(1)
language model
(1)
node classification
(1)
latent space
(1)
graph attention network
(1)
jailbreak attack
(1)
fairness evaluation
(1)
mixture of gaussian
(1)
activation steering
(1)
activation space
(1)
large language model
(1)
graph neural network
(1)
uniform distribution
(1)
refusal suppression
(1)
junta distribution
(1)
Papers
Silenced Biases: The Dark Side LLMs Learned to Refuse
AAAI 2026
Jailbreak Attack Initializations as Extractors of Compliance Directions
EMNLP 2025
Learnable Graph Convolutional Attention Networks
ICLR 2023
Graph Attention Retrospective
JMLR 2023
Learning and testing junta distributions with sub cube conditioning
COLT 2021