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 Google 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.
I am primarily interested in studying how structure helps improve generalization in perception, control and planning. Recently, I have been focusing on effective pre-training and adaptation strategies for large-scale models and large-action models. Please see some of the works below for specifics.
Key Topics: world representations, autonomous agents, self-supervised learning.
The best way to reach me is via email at sai dot mudumba at servicenow dot com
Equivariant Adaptation of Large Pre-trained Models
Arnab Kumar Mondal, Siba Smarak Panigrahi, Sékou-Oumar Kaba, Sai Rajeswar, Siamak Ravanbakhsh.
NeurIPS 2023
paper
Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
Arnab Mondal, Siba Smarak, Sai Rajeswar, Kaleem Siddiqi, Ravanbakhsh
NeurIPS 2023 (under review)
paper
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)
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