I am a second year PhD student at VILAB, EPFL supervised by Prof. Amir Zamir. I am broadly interested in problems at the intersection of machine learning, neurosciene and/or psychology. Currently, I am exploring problems in bio-inspired deep learning for perception, reasoning and computational design.

Previously, I was a Pre-Doctoral Researcher at Google Research India, where I worked with Dr. Pradeep Shenoy on cognitively inspired deep neural networks. I am grateful for the opportunity to work on projects in collaboration with Prof. Ravi Kiran Sarvadevabhatla (IIIT Hyderabad), Prof. Virginia De Sa (UC San Diego) and Dr. Mike Mozer (Google Research), during my time at Google Research.

I am also interested in application of ML to help people with learning and communicative disorders and for promoting and ensuring inclusivity.

I graduated with a Dual Degree, Bachelor and Master of Technology in Computer Science and Engineering from Indian Institute of Technology, Delhi, India in 2019. For more details, check my CV or send me an email.

Publications

How Far Can a 1-Pixel Camera Go?
Rishubh Singh*, Andrei Atanov*, Jiawei Fu*, Isabella Yu, Andrew Spielberg, Amir Zamir
ECCV 2024
project page | pdf

Edges to Shapes to Concepts: Adversarial Augmentation for Robust Vision
Aditay Tripathi, Rishubh Singh, Anirban Chakraborty, Pradeep Shenoy
CVPR 2023
arXiv | pdf

FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing
Rishubh Singh, Pranav Gupta, Pradeep Shenoy, Ravi Kiran Sarvadevabhatla
CVPR 2022
project page | pdf

How much complexity does an RNN architecture need to learn syntax-sensitive dependencies?
Gantavya Bhatt*, Hritik Bansal*, Rishubh Singh*, Sumeet Agrawal (* = Equal Contribution)
ACL'20 : Student Research Workshop | Annual Conference of the Association for Computational Linguistics
abstract| pdf

Indian Institute of Technology, Delhi
2014 - 2019
KTH Royal Institute of Technology, Stockholm
Fall 2016
Graviton Research Capital LLP
2019 - 2020
Google Research India
2020 - 2023
EPFL
2023 - Present