Projects

Things I've built from scratch

TinyVLM-470M

Multimodal

A 470M parameter Vision-Language Model built from scratch with LLaMA 4-style iRoPE, Grouped Query Attention, and Mixture of Experts. Trained on a single RTX 3090 in ~35-40 hours, achieving 64.5% preference accuracy.

Diffusion-Based Data Augmentation

Computer Vision

Controlled benchmark of classical vs diffusion augmentation for few-shot satellite image classification. Fine-tuned SD 1.5 LoRA on EuroSAT, showing selective synthetic augmentation closes to within 0.4% of real-only performance at 64-shot.

Transformer-Based LLM from Scratch

LLM

GPT-style decoder-only transformer implemented from scratch in PyTorch with custom BPE tokenizer, KV-cache optimization, and a training loop with mixed precision, gradient clipping, and early stopping.

Problem Metadata Hider

Chrome Extension

Chrome extension that hides spoiler metadata (difficulty, hints, topics, company tags) on LeetCode and NeetCode problem pages for distraction-free practice.