collaborators

5 papers

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.RO2026

Constrained Decoding for Safe Robot Navigation Foundation Models

Parv Kapoor, Akila Ganlath, Michael Clifford +3

Recent advances in the development of robotic foundation models have led to promising end-to-end and general-purpose capabilities in robotic systems. Trained on vast datasets of si…

cs.CV2025

FACE: Faithful Automatic Concept Extraction

Dipkamal Bhusal, Michael Clifford, Sara Rampazzi +1

Interpreting deep neural networks through concept-based explanations offers a bridge between low-level features and high-level human-understandable semantics. However, existing aut…

cs.CV2025

Do Sparse Subnetworks Exhibit Cognitively Aligned Attention? Effects of Pruning on Saliency Map Fidelity, Sparsity, and Concept Coherence

Sanish Suwal, Dipkamal Bhusal, Michael Clifford +1

Prior works have shown that neural networks can be heavily pruned while preserving performance, but the impact of pruning on model interpretability remains unclear. In this work, w…

cs.CV2025

Smaller is Better: Enhancing Transparency in Vehicle AI Systems via Pruning

Sanish Suwal, Shaurya Garg, Dipkamal Bhusal +2

Connected and autonomous vehicles continue to heavily rely on AI systems, where transparency and security are critical for trust and operational safety. Post-hoc explanations provi…