Anish Madan

I'm a Research Associate at the Robotics Institute, Carnegie Mellon University. I graduated with my Masters in Robotics at CMU, advised by Prof. Deva Ramanan. Here, I have been working on 4D (space-time) dynamic scene reconstruction and leveraging Foundation Models for automating annotation pipelines for Autonomous Vehicle(AV) tasks.

Previously I was an Associate ML Scientist at Wadhwani AI, where I worked on the Baby Anthropometry project led by Dr. Makarand Tapaswi. The project aimed to estimate newborn weight from monocular video to enable timely interventions 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, 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 looking for full-time roles in Computer Vision, Autonomous Vehicles or Robotics starting May 2025. Please reach out if you think I would be a good fit.

Email / GitHub / Google Scholar / LinkedIn / Twitter / CV

	SMORE: Simultaneous Map and Object Reconstruction Nathaniel Chodosh, Anish Madan, Simon Lucey, Deva Ramanan International Conference on 3D Vision (3DV), 2025 arxiv / website /
	Revisiting Few-Shot Object Detection with Vision-Language Models Anish Madan, Neehar Peri, Shu Kong, Deva Ramanan Neural Information Processing Systems, Datasets and Benchmarks Track (NeurIPS), 2024 EVAL-FoMo Workshop, ECCV 2024 arxiv / code / competition / poster /
	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), 2023 arxiv / poster /
	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), 2022 arxiv / code / website / youtube /
	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 /
	C3VQG: Category Consistent Cyclic Visual Question Generation Sarthak Bhagat, Anish Madan, Shagun Uppal, Yi Yu, Rajiv Ratn Shah ACM Multimedia Asia (MMAsia), 2020* arxiv / code / slides / youtube /

Design and source code from Jon Barron's website

Anish Madan

SMORE: Simultaneous Map and Object Reconstruction

Revisiting Few-Shot Object Detection with Vision-Language Models

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

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

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

C3VQG: Category Consistent Cyclic Visual Question Generation