Jai Bardhan

New Delhi, India

Hello 👋 !

My name is Jai. I work as a pre-doctoral researcher at TCS Research where I work with Ramya Hebbalaguppe in the Deep Learning and AI Lab. At TCS my work predominantly revolves around generative models such as diffusion models (such as their evaluation, controllability and interpretability) and 3D computer graphics (viz. curve skeletonizations, DDG).

Prior to joining TCS Research, I completed my Masters Thesis under Dr. Subhadip Mitra in CCNSB IIIT Hyderabad on the topic of “Revisiting Deep Learning for Particle Physics”. I currently work part-time as a research lead — guiding projects related to self-supervised representation learning for foundation models, GNN interpretability and generative modelling.

I am open to discussing interesting ideas in any of these domains. So hit me up if you’d like to collaborate!

You can get my (somewhat) updated CV here.

news

Jul 12, 2024	I have been awarded the Ritesh Tiwari Outstanding MS Thesis Award for 2023 (Best Thesis Award)
Jul 22, 2023	I have been awarded the Gold Medalist Award for the CND Department at IIIT Hyderabad for the highest CGPA of the 2018 incoming batch.

selected publications

Machine learning-enhanced search for a vectorlike singlet B quark decaying to a singlet scalar or pseudoscalar

Jai Bardhan, Tanumoy Mandal, Subhadip Mitra, and 1 more author

Phys. Rev. D, Jun 2023

DOI
Loss function to optimise signal significance in particle physics

Jai Bardhan, Cyrin Neeraj, Subhadip Mitra, and 1 more author

Machine Learning and the Physical Sciences Workshop @ NeurIPS 2024, Sep 2024
ReMOVE: A Reference-free Metric for Object Erasure

Aditya Chandrasekar, Goirik Chakrabarty, Jai Bardhan, and 2 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Sep 2024
CSCD: 3D Object Curve Skeletonization on Continuous Domain

Jai Bardhan, Ramya Hebbalaguppe, Rahul Narain, and 1 more author

Submitted to a top computer vision conference (double-blind), Nov 2024
Constructing sensible baselines for Integrated Gradients

Jai Bardhan, Cyrin Neeraj, and Subhadip Mitra

Accepted at the AI to Accelerate Science and Engineering Workshop @ AAAI 2025, Nov 2024
Unsupervised and lightly supervised learning in particle physics

Jai Bardhan, Tanumoy Mandal, Subhadip Mitra, and 2 more authors

The European Physical Journal Special Topics, Jul 2024

Abs DOI

We review the main applications of machine learning models that are not fully supervised in particle physics, i.e., clustering, anomaly detection, detector simulation, and unfolding. Unsupervised methods are ideal for anomaly detection tasks—machine learning models can be trained on background data to identify deviations if we model the background data precisely. The learning can also be partially unsupervised when we can provide some information about the anomalies at the data level. Generative models are useful in speeding up detector simulations—they can mimic the computationally intensive task without large resources. They can also efficiently map detector-level data to parton-level data (i.e., data unfolding). In this review, we focus on interesting ideas and connections and briefly overview the underlying techniques wherever necessary.