Oleg Rogov
5 papers · 2024–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π
Conference Polyglot
(2)
π
Cross-Pollinator
(5)
πΊοΈ
Taxonomy Completionist
(11)
Conferences
ACL (2)
AAAI (1)
EACL (1)
IJCAI (1)
Top co-authors
Research topics
Keywords
large language model
(2)
sparse autoencoder
(2)
multimodal learning
(1)
privacy preservation
(1)
machine unlearning
(1)
model forgetting
(1)
feature representation
(1)
model alignment
(1)
deep learning model
(1)
language model
(1)
mechanistic interpretability
(1)
ownership verification
(1)
causal intervention
(1)
gradient ascent
(1)
neural network watermarking
(1)
model protection
(1)
trigger set
(1)
model stealing
(1)
model ownership verification
(1)
data removal
(1)
Papers
Feature Drift: How Fine-Tuning Repurposes Representations in LLMs
EACL 2026
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
AAAI 2026
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
ACL 2026
CLEAR: Character Unlearning in Textual and Visual Modalities
ACL 2025
Probabilistically Robust Watermarking of Neural Networks
IJCAI 2024