1. TR2-D2: Off-policy RL for discrete diffusion fine-tuning with multi-objective rewards.
2. Branched Schrödinger Bridge Matching: Released on arXiv and accepted at ICML ExAIT workshop.
3. PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion, accepted at ICML 2025.
4. Review paper on Peptide-Functionalized Nanoparticles for Brain-Targeted Therapeutics, published in Drug Delivery and Translational Research.
Research Experience
Chatterjee Lab: developing theoretical ML frameworks for biological design; Mitchell Lab: designing lipid nanoparticle (LNP)-based delivery vehicles to transport mRNA across the blood-brain barrier.
Education
University of Pennsylvania, dual degree in Computer Science and Business, Jerome Fisher Program.
Background
A third-year undergraduate student researching at the intersection of ML and biological discovery. Also a dual degree student studying computer science and business in the Jerome Fisher Program in Management & Technology.
Miscellany
Enjoys gaining a deep understanding of the theory behind the mechanisms governing the algorithms or biological processes studied. Writes in-depth technical guides, published on Substack, with the most read article being 'A Complete Guide to Spherical Equivariant Graph Transformers'.