Q-Cards
A fine-tuning pipeline that teaches language models to write database query hints, cutting latency by 26% on unseen queries.
I’m a junior at Redmond High School in Washington. I research how machine learning can make computer systems faster, and I like building things from scratch, like a CPU emulator, an interpreter, and a neural network in plain C.
I’m presenting my first paper at NeurIPS in Sydney on December 12.

Advait Badrish, Hanwen Liu, and Ibrahim Sabek.When Not to Hint: Adapting an LLM Query Optimizer to a New Database Instance.MLForSys Workshop at NeurIPS 2026, Sydney.
Language models can be trained to give a database’s query optimizer hints, but they struggle on databases they weren’t trained on. I designed a low-cost pipeline to adapt them, cutting latency 31% compared to PostgreSQL on hinted queries and running 2.79× faster than a model trained on a different database. I’m presenting it in Sydney on December 12.
A fine-tuning pipeline that teaches language models to write database query hints, cutting latency by 26% on unseen queries.
An all-in-one hiking backpack with solar charging, a GPS locator with emergency SOS, and a built-in water filter.
A desktop app that pairs PoseNet with formulas I designed to catch slouching in real time, with 97.3% accuracy.
A convolutional neural network that classifies heartbeat sounds as normal or abnormal with 98% accuracy, plus an Android app so people can screen their own heart sounds.
A new notation for the mridangam and a 21-layer CNN that identifies strokes with 94% accuracy, so recordings can be transcribed automatically.
A phone app that classifies a photo of trash into 7 categories with 97% accuracy and tells you which bin it goes in.
A programming language interpreter written in C
A feedforward neural network in plain C
A water intake tracker
Chess on Discord
A 16-bit CPU emulator
A solver for the card game Set
First-author paper at the MLForSys Workshop, NeurIPS 2026
USA AI Olympiad, Round 2 Silver Medal