Sai Rajeswar

I am a Senior Research Scientist at ServiceNow Research, Montreal team. I completed my Ph.D. in Computer Science at Mila in Université de Montréal, under the supervision of Prof. Aaron Courville. During my Ph.D., I spent time at DeepMind as a Research Scientist intern and at ElementAI as a visiting researcher.

Earlier, I graduated from IIT Delhi, with masters in Computer Science. I worked as a Research Engineer at Xerox Research Centre before joining my Ph.D. Previously, I also graduated with an MSc in Mathematics from SSSIHL, in India.

Research

I am primarily interested in perception and control from limited supervision. Topics of interest include generative interactive models, transfer and pre-training strategies for RL.

Projects

Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels
Sai Rajeswar*, Pietro Mazzaglia*, Tim Verbelen, Alexandre Piche, Bart Dhoedt, Aaron Courville, Alexandre Lacoste.
ICML 2023 (oral)
paper

Diagonal Koopman Operator for Long-Range Dynamics Modelling in Reinforcement Learning
Arnab Mondal, Siba Smarak, Sai Rajeswar, Kaleem Siddiqi, Ravanbakhsh
ICML 2023 (under review)
paper (soon)

Choreographer: Learning and Adapting Skills in Imagination
Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Alexandre Lacoste, Sai Rajeswar
ICLR 2023 (spotlight)(oral)
paper / code

Hyperbolic Deep Reinforcement Learning for Continuous Control
Omar Salemohamed, Edoardo Cetin, Sai Rajeswar, Arnab Kumar Mondal
ICLR 2023 (Tiny paper)
paper / code (soon)

Consistency-CAM: Towards Improved Weakly Supervised Semantic Segmentation Sai Rajeswar, Issam Lardiji, Pau Rodriguez, David Vazquez, Aaron Courville BMVC, 2022
paper

Unsupervised Model-based Pretraining for Data-Efficient Control from Pixels
Sai Rajeswar*, Pietro Mazzaglia*, Tim Verbelen, Alexandre Piche, Bart Dhoedt, Aaron Courville, Alexandre Lacoste.
DARL workshop, @ICML 2022
paper / code (soon)

Multi-label Iterated Learning for Image Classification with Label Ambiguity Sai Rajeswar*, Pau Rodriguez*, Soumye Singhal, David Vazquez, Aaron Courville CVPR, 2022
paper / code

Touch-based Curiosity for Sparse-Reward Tasks
Sai Rajeswar, Cyril Ibrahim, Nitin Surya, Florian Golemo, David Vazquez, Aaron Courville, Pedro O. Pinheiro
CoRL, 2021
paper / code

Pix2shape: Towards unsupervised learning of 3d scenes from images using a view-based representation
Sai Rajeswar, Fahim Mannan, Florian Golemo, Jérôme Parent-Lévesque, David Vazquez, Derek Nowrouzezahrai, Aaron Courville
IJCV, 2020
paper / code

Adversarial computation of optimal transport maps
Jacob Leygonie, Jennifer She, Amjad Almahairi, Sai Rajeswar, Aaron Courville
Preprint, 2019
paper / code

Mutual Information Neural Estimation
Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeswar, Sherjil Ozair, Yoshua Bengio, Aaron Courville, R Devon Hjelm
ICML, 2018
paper / code

Augmented cyclegan: Learning many-to-many mappings from unpaired data
Amjad Almahairi, Sai Rajeswar, Alessandro Sordoni, Philip Bachman, Aaron Courville
ICML, 2018
paper / code

Hierarchical adversarially learned inference
Mohamed Ishmael Belghazi*, Sai Rajeswar*, Olivier Mastropietro, Negar Rostamzadeh, Jovana Mitrovic, Aaron Courville
TADGM workshop, @ICML 2018
paper

Towards text generation with adversarially learned neural outlines
Sandeep Subramanian, Sai Rajeswar, Alessandro Sordoni, Adam Trischler, Aaron C Courville, Chris Pal
NeurIPS, 2018
paper

A deep reinforcement learning chatbot
Iulian V Serban, Chinnadhurai Sankar, Mathieu Germain, Saizheng Zhang, Zhouhan Lin, Sandeep Subramanian, Taesup Kim, Michael Pieper, Sarath Chandar, Nan Rosemary Ke, Sai Rajeswar, …, Yoshua Bengio
NeurIPS demo, 2017
paper

Adversarial Generation of Natural Language
Sai Rajeswar*, Sandeep Subramanian*, Francis Dutil, Chris Pal, Aaron Courville
ACL, RepL4NLP, 2017
paper

A hypothesize-and-verify framework for text recognition using deep recurrent neural networks
Anupama Ray, Sai Rajeswar, Santanu Chaudhury
ICDAR, 2015
paper

Cogito, ergo sum