“
I am a PhD candidate and NPGS Scholar at the EmPACT Lab, School of Electrical and Electronic Engineering (EEE), Nanyang Technological University (NTU), Singapore. My research focuses on efficient perception and reasoning in Vision-Language Models (VLMs), with an emphasis on bio-inspired visual representations and adaptive multimodal learning. I investigate how principles from human visual perception, such as foveated vision and adaptive attention, can be integrated into multimodal systems to enable efficient reasoning under constrained computational and pixel budgets.
Prior to starting my PhD, I pursued a Master of Technology in Computer Science and Engineering at Indian Institute of Technology Gandhinagar. During my master's, my research focused on differentiable rendering and 3D shape analysis, exploring learning-based approaches for geometric understanding and visual reconstruction. I also collaborated with researchers at the National Institute of Mental Health (NIMH), USA, on projects studying animal cognition and behavior using computer vision and pose estimation techniques.
Prior to starting my PhD, I pursued a Master of Technology in Computer Science and Engineering at Indian Institute of Technology Gandhinagar. During my master's, my research focused on differentiable rendering and 3D shape analysis, exploring learning-based approaches for geometric understanding and visual reconstruction. I also collaborated with researchers at the National Institute of Mental Health (NIMH), USA, on projects studying animal cognition and behavior using computer vision and pose estimation techniques.
”