About Me
I am a 1st year PhD scholar in Computer Science (Machine Learning) at Dr. Subhankar Mishra's Lab (@smlab-niser), NISER, India. My academic journey began with a strong foundation in mathematics, which equipped me with a rigorous analytical and problem-solving skillset. This background has proven invaluable in my current research, allowing me to approach complex AI/ML challenges with a unique perspective and a deep understanding of the underlying mathematical principles.
My research focuses on NLPs and Geometric deep learning, primarily GNNs. I am particularly interested in developing novel algorithms, exploring new applications, and addressing ethical considerations.
As a researcher, I am committed to advancing of AI/ML through innovative research and scholarly contributions.
Research
Exploration of expressivity of GNDEs, focusing on the trade-off between privacy and expressivity. The project aims to develop a comprehensive understanding of the continuous part of the message passing of NDEs and the impact of these mechanisms on their learning capabilities in GNNs.
Large Language Models (LLMs) have revolutionized numerous fields with their impressive language understanding and generation capabilities. However, their reliability is hindered by several robustness issues, particularly the generation of nonsensical or factually incorrect content, known as hallucinations. This phenomenon poses a considerable challenge to the reliability of LLMs in real-world scenarios. This survey comprehensively explores these challenges, moving beyond adversarial robustness to focus on critical factors such as out-of-distribution (OOD) generalization, bias and fairness, contextual understanding, and shortcut learning.
Publications
CV
For a detailed overview of my academic and professional background, please refer to my Curriculum Vitae.
Download CV