🌿 Research Focus
Shilpy is developing efficient and explainable Vision Transformer architectures that reduce compute overhead while improving transparency for real-world computer vision applications. Her work bridges performance, interpretability, and practical deployment by designing lightweight transformer blocks, attention visualization strategies, and model compression techniques.
Research Details
Investigating Advances in Vision Transformers: Designing Efficient and Explainable Models
Efficient Vision Transformers
Building transformer models that are faster and less memory-intensive for practical deployment.
Explainable AI
Developing techniques to reveal why transformer-based vision systems make specific predictions.
Attention Mechanisms
Studying attention patterns to improve robustness and interpretability in vision tasks.
Real-World Computer Vision
Focusing on applications in healthcare, automation, and agricultural imaging.
Key Research Keywords
Publications
Shilpy Kaur et al., "Proximal Vision Transformer" Published
Educational Background
Technical Skills
Programming Languages
Tools & Platforms
Achievements & Recognition
Teaching Assistantship
Contact Information
"I like working on problems that sit at the intersection of efficiency and understanding, building models that not only perform well but also make sense to people."