Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Interpreting Physics in Video Encoders using Multi-Object Interaction Videos
Ayushi Mehrotra, Sai Vidyaranya Nuthalapati
Video encoder models are increasingly used as world models for physical AI, where a policy plans by rolling out the latent, so what physics the latent holds bounds what the agent c…
cs.CV2026
H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers
Ayushi Mehrotra, Dipkamal Bhusal, Michael Clifford +1
Feature attribution methods explain the predictions of deep neural networks by assigning importance scores to individual input features. However, most existing methods focus solely…
cs.CV2025
Concept-Based Masking: A Patch-Agnostic Defense Against Adversarial Patch Attacks
Ayushi Mehrotra, Derek Peng, Dipkamal Bhusal +1
Adversarial patch attacks pose a practical threat to deep learning models by forcing targeted misclassifications through localized perturbations, often realized in the physical wor…