Latest News
- Joined RBC Borealis as a Machine Learning Researcher in Montréal (September 2026).
- Our paper The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show was accepted as a Spotlight at NeurIPS 2026 (arXiv).
- Our paper When Does Predictive Inverse Dynamics Outperform Behavior Cloning? was accepted at ICML 2026.
- Our paper Augmentations for Robust and Efficient Imitation Learning in Streamed Video Games was accepted as an Oral at IEEE CoG 2026.
- Our paper Structured Representation Learning with Locally Linear Embeddings and Adaptive Feature Fusion was accepted at TMLR 2026.
- Completed a Research Internship at Microsoft Research Cambridge on sample efficient imitation learning.
- Received Outstanding Reviewer Awards at ICML 2025 and ICCV 2023.
Research Interests
At RBC Borealis, I work on applying machine learning techniques for commercial credit.
Beyond RBC, my research focuses on reinforcement learning, representation learning, and world models. I am particularly interested in how agents can learn predictive and structured representations that support efficient learning, exploration, planning, and generalization, and in connecting reinforcement learning with video diffusion models, self supervised learning, and imitation learning.
Experience
Machine Learning Researcher
Sep 2026 – present
RBC Borealis, Montréal, Canada
Applying machine learning techniques for commercial credit.
Research Intern
May 2025 – Aug 2025
Microsoft Research Cambridge, United Kingdom
Worked on improving representation learning approaches for sample efficient
imitation learning in video game environments.
Scientist in Residence
Jun 2024 – Sep 2024
4Division and Mila, Montréal, Canada
Worked on scalable Robotics Transformer models trained on diverse robotic data
for strong real world generalization.
Machine Learning Research Intern
May 2023 – Aug 2023
RBC Borealis, Montréal, Canada
Developed an unsupervised outlier detection framework in continuous time event
sequences using reinforcement learning.
Researcher, Data and Decision Sciences
Nov 2019 – Jan 2022
Tata Consultancy Services Research and Innovation, Mumbai, India
Applied reinforcement learning to multi product, multi node inventory management,
improving performance over existing industry approaches, and developed RL methods
for delayed actions and observations.
Research Intern
May 2015 – Jul 2015
Indian Statistical Institute, Kolkata, India
Worked on OCR and character segmentation methods for Bengali and English text.
Selected Publications
* denotes equal contribution
The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
Augmentations for Robust and Efficient Imitation Learning in Streamed Video Games
Structured Representation Learning with Locally Linear Embeddings and Adaptive Feature Fusion
Behaviour Discovery and Attribution for Explainable Reinforcement Learning
Unsupervised Event Outlier Detection in Continuous Time
Task Oriented Slot Based Cumulant Discovery in General Value Functions
Spectral Temporal Contrastive Learning
Follow your Nose: Using General Value Functions for Directed Exploration in Reinforcement Learning
SIBRE: Self Improvement Based Rewards for Adaptive Feedback in Reinforcement Learning
Awards and Service
- Outstanding Reviewer, ICML 2025
- Outstanding Reviewer, ICCV 2023
- McGill Engineering Doctoral Award
- TCS Citation Award, 2021 and 2022
- Scholarship for Academic Excellence, State Electrical Engineers’ Association
Education
- McGill University and Mila
PhD Candidate in Electrical and Computer Engineering, 2022 – present - University of Alberta
MSc in Computing Science, 2017 – 2019 - Jadavpur University
BE in Electrical Engineering, 2013 – 2017