Harsh Pal

I'm a Data Scientist at Mastercard, AI Garage in Gurgaon, where I mostly work on Credit-Card fraud detection techniques.

I graduated from IIT Bombay in 2023. I completed my Bachelors in Electrial Engineering and Masters in Communication and Signal Processing. I was advised by Prof. Biplab Bannerjee, under whom I completed my Master's thesis on Towards Novel Domain Adaptation Techniques.

Email  /  CV  /  Scholar  /  Github

“A genius is the man who can do the average thing when everyone else around him is losing his mind”

- Napoleon

News!!

[28/05/25]    SALE-MLP paper accepted at IJCAI'25.

[26/07/23]    Joined Mastercard AI Garage.

[12/04/23]    3D Shape Retrieval paper paper accepted at WACV'24

[03/03/23]    Ad-clip paper accepted at ICCV'23

Research

I'm interested in Deep Learning, Domain Adaptation, Generative AI, Federated Learning, and Blockchains.

We introduce AD-CLIP, a domain-agnostic prompt learning strategy for CLIP that aims to solve the DA problem in the prompt space.

Objective of this work is to align the images and shapes separately from both domains while simultaneously learn a shared embedding space for the 2D and 3D modalities.