Research

My research interests lie broadly in trustworthy AI and human-machine collaboration. I am also excited by applications of learning algorithms in cost sensitive domains such as healthcare and criminal justice. Given constraints and feedback on a model provided by external stakeholders, I want to design algorithms that are maximally reliable / performant under the constraint set.

Papers Currently Under Review

1. Varun Babbar*, Stark Guo *, Cynthia Rudin
   What is different between these datasets?
   Submitted to Journal of Machine Learning Research (JMLR), 2024.
   Paper

2. Another paper recently submitted to AISTATS 2025 - details to be added soon!

Conference Publications (Refereed and Archived)

1. Varun Babbar, Umang Bhatt, Adrian Weller
   On the Utility of Prediction Sets in Human-AI Teams
   International Joint Conference on Artificial Intelligence (IJCAI), 2022. (Oral)
   Paper Poster

2. Antonios Georgiadis*, Varun Babbar*, Fran Silavong, Sean Moran, Rob Otter
   ST-FL: Style Transfer Preprocessing in Federated Learning for COVID-19 segmentation
   SPIE Medical Imaging 2022: Imaging Informatics for Healthcare, Research, and Applications
   Paper Poster

3. Aamir Mustafa, Aliaksei Mikhailiuk, Dan Andrei Iliescu, Varun Babbar, Rafal K Mantiuk
   Training a Task-Specific Image Reconstruction Loss
   Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022
   Paper

Workshop Publications (Refereed)

1. Varun Babbar, Umang Bhatt, Miri Zilka, Adrian Weller
   Conformal Prediction for Resource Prioritisation in Predicting Rare and Dangerous Outcomes
   NeurIPS Workshop on Human in the Loop Learning, 2022
   Paper Poster

2. Agathe Lherondelle, Varun Babbar, Yash Satsangi, Fran Silavong, Shaltiel Eloul, Sean Moran.
   Topical: Learning Repository Embeddings from Source Code using Attention
   In The 1st Workshop on Software Engineering Challenges in Financial Firms, International Conference on Software Engineering (ICSE) 2024
   Paper

Patents

1. Antonios Georgiadis, Fanny Silavong, Sean Moran, Rob Otter, Varun Babbar
   Systems and Methods For Noise Agnostic Federated Learning
   Patent

2. Another one in progess - relating to machine learning on source code

Thesis

1. Varun Babbar
   Set Valued Predictions for Human-AI Teams
   MEng Thesis - University of Cambridge (Prize for outstanding thesis)
   Thesis