Narine Kokhlikyan
7 papers · 2013–2024 · 4 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
🏃
Academic Marathon · Half
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
representation learning
(1)
image restoration
(1)
natural language processing
(1)
feature attribution
(1)
model interpretability
(1)
model debugging
(1)
image representation
(1)
data privacy
(1)
convolutional neural network
(1)
convolutional network
(1)
pre-trained model
(1)
influence function
(1)
vision-language model
(1)
privacy leakage
(1)
training data
(1)
model explainability
(1)
generative language model
(1)
slice discovery
(1)
small object detection
(1)
spatial generalization
(1)
Papers
Measuring Dejavu Memorization Efficiently
NeurIPS 2024
Error Discovery By Clustering Influence Embeddings
NeurIPS 2023
Mind the Pool: Convolutional Neural Networks Can Overfit Input Size
ICLR 2023
Using Captum to Explain Generative Language Models
EMNLP 2023
Fine-grained Interpretation and Causation Analysis in Deep NLP Models
NAACL 2021
Mind the Pad -- CNNs Can Develop Blind Spots
ICLR 2021
Measuring the Structural Importance through Rhetorical Structure Index
NAACL 2013