The Art of Translation
What if your model could just look where it needed to? Exploring attention mechanisms in sequence-to-sequence learning and how they revolutionize machine translation.
Computer Science and Mathematics at Georgia Tech. Focused on Machine Learning and Mathematical Modeling.
Worked on Fraud Models at Credit Karma and Point of Sale (PoS) systems at NCR. Former competitive swimmer and used to solve math olympiad problems for fun! Indian National Math Olympiad finalist and a Top 300 rank on the Putnam Math Contest.
What if your model could just look where it needed to? Exploring attention mechanisms in sequence-to-sequence learning and how they revolutionize machine translation.
Benchmarking Flash Attention v1 and v2 in Triton against a naive PyTorch implementation of Scaled Dot Product Attention and Multi Headed Attention.
Worked with Prof. Clio Andris on geographic visualizations and spatial information theory.
A Design Space of Node Placement Methods for Geospatial Network Visualizations.
Benchmarking Flash Attention v1 and v2 in Triton against a naive PyTorch implementation of Scaled Dot Product Attention and Multi Headed Attention.
Trained a sequence-to-sequence model with and without the attention mechanism to translate natural language to Python snippets.