Dipkamal Bhusal
Scholar

Dipkamal Bhusal

Google Scholar ID: AAxpmiMAAAAJ
Rochester Institute of Technology
InterpretabilityExplainabilityDeep LearningReliable AILarge Language Models
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
264
 
H-index
7
 
i10-index
6
 
Publications
20
 
Co-authors
17
list available
Contact
No contact links provided.
Publications
10 items
Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation
2026
Cited
0
H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers
2026
Cited
0
Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing
2026
Cited
0
AthenaBench: A Dynamic Benchmark for Evaluating LLMs in Cyber Threat Intelligence
2025
Cited
0
FACE: Faithful Automatic Concept Extraction
2025
Cited
0
Concept-Based Masking: A Patch-Agnostic Defense Against Adversarial Patch Attacks
2025
Cited
0
Learning to Look: Cognitive Attention Alignment with Vision-Language Models
2025
Cited
0
Smaller is Better: Enhancing Transparency in Vehicle AI Systems via Pruning
2025
Cited
0
Resume (English only)
Co-authors
17 total
Nidhi Rastogi
Nidhi Rastogi
Assistant Professor, Rochester Institute of Technology, NY
Tanvirul Alam
Tanvirul Alam
PhD Student, Rochester Institute of Technology
Youngja Park
Youngja Park
IBM T. J. Watson Research Center
Le Nguyen
Le Nguyen
Research Scientist, Soar Technologies. PhD Student, Rochester Institute of Technology
Michael Clifford
Michael Clifford
Principal Researcher, Toyota InfoTech Labs
Co-author 6
Co-author 6
Co-author 7
Co-author 7
Co-author 8
Co-author 8