Anish Madan

I'm a second-year Masters student at the Robotics Institute, Carnegie Mellon University, advised by Dr. Deva Ramanan. I'm currently working on leveraging multi-modal foundation models to develop techniques that work in limited data settings.

Previously I was an Associate ML Scientist at Wadhwani AI, working on the Baby Anthropometry project (under the guidance of Dr. Makarand Tapaswi. The project's goal is to estimate weight of newborns from a monocular video, in order to provide timely intervention via healthcare providers for low-birth weight babies.

Prior to joining the industry, I graduated from IIIT-Delhi. with my Bachelor's in Computer Science and Applied Mathematics. I worked on defending against adversarial attacks as part of my Bachelor's Thesis, advised by Dr. Saket Anand. I also had the fortune of working with Dr. Ojaswa Sharma, Dr.Ranjitha Prasad, Dr. Rajiv Ratn Shah at IIIT-Delhi.

I am actively looking for PhD opportunities starting Fall 2024. Please reach out if you think I might be a good fit for your lab.

Email  /  GitHub  /  Google Scholar  /  LinkedIn  /  Twitter

profile photo
project image

SLI-pSp: Injecting Multi-Scale Spatial Layout in pSp


Aradhya Neeraj Mathur*, Anish Madan*, Ojaswa Sharma"
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021
arxiv / poster /

project image

REGroup: Rank-aggregating Ensemble of Generative Classifiers for Robust Predictions


Lokender Tiwari, Anish Madan, Saket Anand, Subhashis Banerjee"
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021
arxiv / code / website / youtube /

project image

B-SMALL: A Bayesian Neural Network approach to Sparse Model-Agnostic Meta-Learning


Anish Madan, Ranjitha Prasad"
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
arxiv / code / slides /

project image

C3VQG: Category Consistent Cyclic Visual Question Generation


Sarthak Bhagat*, Anish Madan*, Shagun Uppal*, Yi Yu, Rajiv Ratn Shah
ACM Multimedia Asia, 2020
arxiv / code / slides / youtube /





Design and source code from Jon Barron's website