Get started
Author

Narine Kokhlikyan

Captum: A unified and generic model interpretability library for PyTorch
2020 · Kokhlikyan, Narine, Miglani, Vivek, et al. · arXiv (Cornell University) · 1,240
PDF
XAIR: A Framework of Explainable AI in Augmented Reality
2023 · Xuhai Xu, Anna Yu, et al. · CHI Conference on Human Factors in Computing Systems · 96
PDF
How much do language models memorize?
2025 · Morris, John X., Sitawarin, Chawin, et al. · arXiv (Cornell University) · 89
PDF
Mind the Pad -- CNNs can Develop Blind Spots
2020 · Alsallakh, Bilal, Kokhlikyan, Narine, et al. · arXiv (Cornell University) · 72
PDF
Using Captum to Explain Generative Language Models
2023 · Vivek Miglani, Aobo Yang, et al. · Workshop for NLP Open Source Software (NLP-OSS) · 49
PDF
RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection
2025 · Wen, Yuxin, Zharmagambetov, Arman, et al. · arXiv (Cornell University) · 39
PDF
Investigating Saturation Effects in Integrated Gradients
2020 · Miglani, Vivek, Kokhlikyan, Narine, et al. · arXiv (Cornell University) · 32
PDF
Method cards for prescriptive machine-learning transparency
2022 · David Adkins, Bilal Alsallakh, et al. · IEEE/ACM International Conference on AI Engineering – Software Engineering for AI (CAIN) · 23
Prescriptive and Descriptive Approaches to Machine-Learning Transparency
2022 · David Adkins, Bilal Alsallakh, et al. · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · 12
PDF
Investigating sanity checks for saliency maps with image and text classification
2021 · Kokhlikyan, Narine, Miglani, Vivek, et al. · arXiv (Cornell University) · 11
PDF
Building Recommender Systems with PyTorch
2020 · Dheevatsa Mudigere, Maxim Naumov, et al. · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · 6
Fine-grained Interpretation and Causation Analysis in Deep NLP Models
2021 · Hassan Sajjad, Narine Kokhlikyan, et al. · 5
PDF
Z0-Inf: Zeroth Order Approximation for Data Influence
2025 · Kokhlikyan, Narine, Chaudhuri, Kamalika, et al. · arXiv (Cornell University) · 4
PDF
Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
2025 · Wannan, Yang, et al. · arXiv (Cornell University) · 4
PDF
Error Discovery By Clustering Influence Embeddings
2023 · Fulton Wang, Julius Adebayo, et al. · neural information processing systems · 3
PDF
Bias Mitigation Framework for Intersectional Subgroups in Neural Networks
2022 · Kokhlikyan, Narine, Alsallakh, Bilal, et al. · arXiv (Cornell University) · 3
PDF
A Tour of Visualization Techniques for Computer Vision Datasets
2022 · Alsallakh, Bilal, Bhattacharya, Pamela, et al. · arXiv (Cornell University) · 3
PDF
Explainable Interfaces for Rapid Gaze-Based Interactions in Mixed Reality
2024 · Yu, Mengjie, Harris, Dustin, et al. · arXiv (Cornell University) · 2
PDF
Muse Glimmer 30B: An On-Device Agentic Model
2026 · Abtahizadeh, Arash Ebrahim, Aghamelu, Muna, et al. · arXiv (Cornell University) · 1
PDF
Privacy Blur: Quantifying Privacy and Utility for Image Data Release
2025 · Mahloujifar, Saeed, Kokhlikyan, Narine, et al. · arXiv (Cornell University) · 1
PDF
On Symmetries in Convolutional Weights
2025 · Alsallakh, Bilal, Wroge, Timothy, et al. · arXiv (Cornell University) · 1
PDF
Measuring the Structural Importance through Rhetorical Structure Index
2013 · Kokhlikyan, N., Waibel, A., et al. · 1
Measuring Déjà vu Memorization Efficiently
2025 · Kokhlikyan, Narine, Jayaraman, Bargav, et al. · arXiv (Cornell University)
PDF
Measuring Dejavu Memorization Efficiently
2024 · Narine Kokhlikyan, Bargav Jayaraman, et al. · neural information processing systems
Fine-grained Interpretation and Causation Analysis in Deep NLP Models
2021 · Sajjad, Hassan, Kokhlikyan, Narine, et al. · arXiv (Cornell University)
PDF
Works count: 29
Citation count: 1,697
H-index: 10
I10-index: 10
Year
Topic
Type