Hello 👋 I'm a Statistics & Data Science student at Ludwig Maximilian University of Munich (SIST scholar), focused on deep learning and language models. Previously founded Kaza Street Tech (street food order management in India), recognized in Shark Tank Campus Special Round and as a top student-led startup by Startup India.
Notes on deep learning, language models, and ML in production.
Loading latest posts...
Honors program run with LMU, TUM, and partners: about 25 students per cohort, team projects at the intersection of technology, product, and business. Alumni have founded 9+ unicorns; affiliated companies have raised more than €9B.
Making AI usable on resource-constrained hardware, including many feature phones.
We are exploring distillation during pretraining across all 22 Indic languages. So far we have compressed models by up to 8× and are pushing toward 20×. This phase focuses on ModernBERT-style distillation for Indic languages, targeting a milestone around June 2026.
Understanding deep learning by building it from the ground up.
Creating my own PyTorch-like library from scratch to deeply understand the fundamentals and use it to train Indic models for agentic use cases.
Smaller models for gene network dynamics.
Distilling Geneformer (single-cell expression to network dynamics) into compact students, roughly 10M to 4.5M / 3M / 2M parameters, using far less data and compute while keeping reasonable MLM quality.
Code Reproducibility Checker: Tool for systematic verification of research code (with Dr. Anne-Laure).