Mathematics & Computer Science · BITS Pilani, Goa

Hi, I'm Shlok.

I'm a final year undergraduate at BITS Pilani, Goa, dual majoring in Mathematics and Computer Science. I'm currently a visiting scholar supervised by Dr. Alan Yuille at Johns Hopkins University, working on continual learning through the lens of mechanistic interpretability for my thesis.

My path here was indirect. I grew up moving across India, picking up varied cultures and languages along the way, and a keen interest in mathematics. In college I built deep learning systems for a Mars rover team, started research in statistical learning theory under Dr. Snehanshu Saha, and submitted my first paper in my second year, under Dr. JK Sahoo.

We are not students of some subject matter but students of problems. And problems may cut right across the border of any subject matter or discipline. Karl Popper
Research

I'm interested in understanding how neural networks learn: how they extract meaningful representations from data, and why their learning dynamics unfold the way they do. I approach this through deep learning theory and mechanistic interpretability, studying the internal structure that emerges during training and what it reveals about generalisation. More broadly, I'm drawn to problems at the interface of mathematics, machine learning, and the brain.

Deep Learning Theory & Learning Mechanics·Mechanistic Interpretability·Computational Neuroscience & Cognitive Science·Computer Vision

Papers
Matching High-Dimensional Geometric Quantiles for Test-Time Adaptation of Transformers and Convolutional Networks Alike

Sravan Danda, Aditya Challa, Shlok Mehendale, Snehanshu Saha · APPCAIR, BITS Pilani · Preprint, 2026

A Radon-Nikodým Perspective on Anomaly Detection: Theory and Implications

Shlok Mehendale, Aditya Challa, Rahul Yedida, Sravan Danda, Santonu Sarkar, Snehanshu Saha · APPCAIR, BITS Pilani · Preprint, 2025

Atmospheric Noise-Resilient Image Classification in a Real-World Scenario: Using Hybrid CNN and Pin-GTSVM

Shlok Mehendale, Jajati Keshari Sahoo, Rajendra Kumar Roul · BITS Pilani · Preprint, 2025

Benchmarking Anomaly Detection Algorithms: Deep Learning and Beyond

Shanay Mehta*, Shlok Mehendale*, Nicole Fernandes*, Jyotirmoy Sarkar, Santonu Sarkar, Snehanshu Saha · APPCAIR, BITS Pilani · Preprint, 2024 · *Equal contribution