Ashkan Khakzar

Computer Science · Physical Sciences

7h-index169citations45works0.92yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Explainable Artificial Intelligence (XAI)(15), Adversarial Robustness in Machine Learning(14), COVID-19 diagnosis using AI(8), Radiomics and Machine Learning in Medical Imaging(7), Machine Learning in Healthcare(7)

Publications45 total

Towards Understanding Multimodal Fine-Tuning: Spatial Features
arXiv (Cornell University)·2026Open Access
Towards Understanding Multimodal Fine-Tuning: Spatial Features
arXiv (Cornell University)·2026Open Access
Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval
arXiv (Cornell University)·2025Open Access
Mixture of Experts Made Intrinsically Interpretable
arXiv (Cornell University)·2025Open Access
AlignGuard: Scalable Safety Alignment for Text-to-Image Generation
arXiv (Cornell University)·2024Open Access
Learnable Sparsity for Vision Generative Models
arXiv (Cornell University)·2024Open Access
Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models
arXiv (Cornell University)·2024Open Access
Latent Guard: A Safety Framework for Text-to-Image Generation
Lecture notes in computer science·2024· 7 cited
Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders
arXiv (Cornell University)·2024· 1 citedOpen Access
The Cognitive Revolution in Interpretability: From Explaining Behavior to Interpreting Representations and Algorithms
arXiv (Cornell University)·2024· 1 citedOpen Access
Learning Visual Prompts for Guiding the Attention of Vision Transformers
arXiv (Cornell University)·2024· 1 citedOpen Access
Latent Guard: a Safety Framework for Text-to-image Generation
arXiv (Cornell University)·2024· 2 citedOpen Access
On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributions
arXiv (Cornell University)·2024Open Access
Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models
2024
A Survey on Transferability of Adversarial Examples across Deep Neural Networks
arXiv (Cornell University)·2023· 11 citedOpen Access
AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments
arXiv (Cornell University)·2023· 1 citedOpen Access
A Dual-Perspective Approach to Evaluating Feature Attribution Methods
arXiv (Cornell University)·2023Open Access
Pixel-Level Explanation of Multiple Instance Learning Models in Biomedical Single Cell Images
arXiv (Cornell University)·2023Open Access
Pixel-Level Explanation of Multiple Instance Learning Models in Biomedical Single Cell Images
Lecture notes in computer science·2023· 9 cited
CheXplaining in Style: Counterfactual Explanations for Chest X-rays using StyleGAN
arXiv (Cornell University)·2022· 5 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Nassir Navab(28), Seong Tae Kim(14), Yawei Li(7), Philip Torr(7), Soroosh Baselizadeh(7), Matthias Keicher(6), Jindong Gu(5), Daniel Rueckert(4), Saurabh Khanduja(4), Risto Kojcev(3), Oliver Zettinig(3), Yang Zhang(3), Runtao Liu(3), Qifeng Chen(3), Philip H. S. Torr(3), Fabio Pizzati(3), Christian Rupprecht(3), Jan S. Kirschke(3), Benedikt Wiestler(3), Kristina Mach(3)