I'm a PhD student at Mila - Quebec AI Institute and University of Montreal with Aishwarya Agrawal. I was previously a visiting researcher at ServiceNow Research. I received an MSc in CS from University of Saskatchewan and BSc in CS from Noakhali Science and Technology University.
I’m driven to build AI systems that truly understand the physical world. My work centers on two fronts: learning deep visual representations, and developing generative world models, with a particular focus on diffusion and flow matching models. I’m fascinated by scaling foundation models and reinforcement learning to superhuman capabilities, and how these advances connect to the broader challenges of alignment and the profound economic shifts AI will bring.
See my Google Scholar for a full list of publications.
CulturalVQA: Benchmarking Vision Language Models for Cultural Knowledge
EMNLP'24 Oral
February 4-6, 2026 • Mila, Montreal
I'm co-organizing this workshop that brings together researchers working on world models, generative models, and their applications in AI systems.