Nilakshan Kunananthaseelan

I am a PhD student at the ECSE, part of the Faculty of Engineering at Monash University, where I work on customizing foundational models for out-of-distributions. My PhD advisor is A/Prof.Mehrtash Harandi.

Prior to joining Monash University, I was working at Analog Inference. I primarily designed computer vision algorithms for efficient hardware ASICs. Additionally, I worked on text anlytics software API at ExentAI, and I was involved in creating an OCR pipeline dedicated to digitizing Tamil documents at Noolaham project.

I completed my undergraduate study at the University of Moratuwa, with a major in Electronic and Telecommunication Engineering. My undergraduate thesis was advised by Dr. Ajit Pasqual.

Email  /  CV  /  GitHub  /  Google Scholar  /  LinkedIn  /  Twitter  / 

"Don't doubt yourself, son. Doubt kills." — Robert McCall

"Progress. Not Perfection." — Robert McCall

"If everything seems under control, you're not going fast enough." — Mario Andretti

Research

I have a keen interest in several areas of artificial intelligence, particularly in computer vision, multimodal representation learning, and the development of few-shot learning methods. My focus involves exploring innovative techniques within these domains to tackle complex challenges and contribute to advancing the field of AI.
Research Statement

LaViP: Language-Grounded Visual Prompts

We introduce a language-grounded visual prompting method to adapt the visual encoder of vision-language models for downstream tasks.

Undergraduate Projects

My journey into machine learning and computer vision began with a project, igniting my deep interest in these fields.

Machine-based detection and classification for bone marrow aspirate differential counts: initial development focusing on nonneoplastic cells

We introduce a deeplearning pipeline for detection and classification of whiteblood cells from bonemarrow slide images.

Design and source code from Jon Barron's website