Prateek Munjal — accepted AI-conference papers

2026

BioToken and BioFM – Biologically-Informed Tokenization Enables Accurate and Efficient Genomic Foundation Models

Aleksandr Medvedev, Karthik Viswanathan, Praveenkumar Kanithi, Kirill Vishniakov, Prateek Munjal, Clement Christophe +4

ICML 2026poster

Existing genomic foundation models (GFMs) typically treat DNA as raw nucleotide sequences, often overlooking the regulatory context required to interpret genetic variation accurately. We introduce BioToken, a tokenization framework that directly encodes variants and biological annotations into genom…

Cited by 0 Source ↗Scholar ↗

2022

Towards Robust and Reproducible Active Learning Using Neural Networks

Prateek Munjal, Nasir Hayat, Munawar Hayat, Jamshid Sourati, Shadab Khan

CVPR 2022poster

Active learning (AL) is a promising ML paradigm that has the potential to parse through large unlabeled data and help reduce annotation cost in domains where labeling entire data can be prohibitive. Recently proposed neural network based AL methods use different heuristics to accomplish this goal. I…

Cited by 83 PDF ↗code ↗Scholar ↗

2019

Semantically Aligned Bias Reducing Zero Shot Learning

Akanksha Paul, Narayanan C. Krishnan, Prateek Munjal

CVPR 2019poster

Zero shot learning (ZSL) aims to recognize unseen classes by exploiting semantic relationships between seen and unseen classes. Two major problems faced by ZSL algorithms are the hubness problem and the bias towards the seen classes. Existing ZSL methods focus on only one of these problems in the co…

Cited by 99 PDF ↗Scholar ↗