research
Research projects at Mila and selected past work. † denotes ongoing projects.
-
2026ONGOING
Discrete Diffusion for Molecular Generation with RL and Natural Language Steering
Université de Montréal, April 2026
Learns drug-like molecule representations through discrete masked diffusion over SELFIES, with 100% chemical validity by construction. REINFORCE with per-step gradient accumulation steers generation toward desired properties, improving drug-likeness by 12.8%. Natural language conditioning via SciBERT cross-attention reaches 76% of SOTA at 15% of the parameter count.
-
2025ONGOING
Reinforcement Learning in Non-Stationary Environments: Loss of plasticity and evolutionary remedies
Ongoing research · Mila, 2025–present
Investigating the loss of plasticity phenomenon in deep RL agents and experimenting with evolutionary algorithms to overcome it.
-
2021THESIS
Progressive Conformer for Image Classification
NIT Karnataka, 2021
A hybrid architecture combining Transformers and CNNs at the attention level for progressive feature learning in image classification.