• Research Assistant at NAAMII (MMLL research Group)
  • Computer Engineering graduate from IOE Pulchowk Campus
  • Contributed to ARCADE Challenge at MICCAI 2023
Sanjay Bhandari is a Research Assistant at NAAMII working in the MMLL group. He graduated in Computer Engineering from Pulchowk Campus, IOE, and specializes in few-shot learning, multimodal learning, and computer vision applications for medical AI. He has been actively involved in the ARCADE Challenge at MICCAI 2023, contributing to advancing medical image analysis techniques. His research on adversarial few-shot learning addresses the challenge of building robust models that can learn from limited labeled examples while being resistant to adversarial perturbations.

Publications

2025
Out of Distribution Detection in Gastrointestinal Vision by Estimating Nearest Centroid Distance Deficit
Sandesh Pokhrel, Sanjay Bhandari, Sharib Ali, Tryphon Lambrou, Anh Nguyen, Yash Raj Shrestha, Angus Watson, Danail Stoyanov, Prashnna Gyawali, Binod Bhattarai
2025
Hallucination-Aware Multimodal Benchmark for Gastrointestinal Image Analysis with Large Vision-Language Models
Bidur Khanal, Sandesh Pokhrel, Sanjay Bhandari, Ramesh Rana, Nikesh Shrestha, Ram Bahadur Gurung, Cristian Linte, Angus Watson, Yash Raj Shrestha, Binod Bhattarai
2024
TTA-OOD: Test-time Augmentation for Improving Out-of-Distribution Detection in Gastrointestinal Vision
Sandesh Pokhrel, Sanjay Bhandari, Eduard Vazquez, Tryphon Lambrou, Prashnna Gyawali, Binod Bhattarai
2024
Cross-Task Data Augmentation by Pseudo-label Generation for Region Based Coronary Artery Instance Segmentation
Sandesh Pokhrel, Sanjay Bhandari, Eduard Vazquez, Yash Raj Shrestha, Binod Bhattarai