Publications

Lists

Stable Reinforcement Learning for Multimodal Scientific Graph QA

Clipped Policy Gradient Optimization with Policy Drift (CPGD) is employed on the Sci-GraphQA dataset to enhance the Qwen-VL 2.5 model.

AIREINFORCEMENT LEARNINGLLM

NestedVGG: A Novel Deep Learning-based Architecture for Brain Tumour Diagnosis

This paper presents an automated system for brain tumor detection using DL on MRI scans.

AIMACHINE LEARNING

Revolutionizing Pandemic Healthcare: Mask Detection and Patient Face Recognition

In this study, we have proposed a state-of-the-art patient face detection model and mask detection

AIMACHINE LEARNING

Combining Focal loss with Cross-entropy loss for Pneumonia Classification with a Weighted Sampling Approach

This study leverages the fine-tuned MobileNetV2 model for Pneumonia detection, incorporating a hybrid of two loss functions.

AIMACHINE LEARNING