MNIT, Jaipur
JECRC University
JIIT, Noida
JIIT, Noida
My research explores how deep neural networks enable machines to understand, process and generate human language. I am interested in transformer architectures, attention mechanisms, language modeling, representation learning, text generation, summarization, and other NLP applications.
I am fascinated by large language models and multimodal systems capable of understanding and generating information across text, images and other modalities. My interests include Vision-Language Models, Multimodal Learning, Prompt Engineering, Retrieval Augmented Generation (RAG), and emerging Generative AI techniques.
A computer vision application that captures a user's yoga posture through a webcam and predicts the corresponding yoga pose using deep learning.
Python • TensorFlow • OpenCV • CNN
A smart navigation system for visually impaired individuals that detects obstacles using sensors mounted on a walking cane and alerts users in real time.
Arduino • Sensors • IoTNatural Language Processing
Deep Learning
Transformers
Generative and Multimodal AI
DSA, DBMS
C/C++, Java, Python
SQL, HTML, CSS, JS
HackerRank SQL 5⭐
LeetCode DSA (C++)