This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

portfolio

Dancing Bipedal Robot

Dancing Robot, designed as part of Robotics Studio, Spring 2021.

Rapidly Custimizable HVAC Simulator for Reinforcement Learning

A Lightweight Calibrated Simulation Enabling Efficient Offline Learning for Optimal Control of Real Buildings, in collaboration with Google, Fall 2023.

Backend For Reasoning About Interaction Networks

Tool that uses formal verification to analyze gene interactions in cells.

Chess Engine in C++

Powerful Chess engine using modern techniques. image source

Didactic Implementation of Counterfactual Regret Minimization on Kuhn Poker

Easy to understand implementation of CFR on Kuhn Poker, to help people learn about the algorithm. image source

Evolved walking Robot

Evolved walking Robot, designed as part of Evolutionary Computation, Spring 2022.

Automated Punctuation Tagging for Medieval Hebrew Manuscripts

LSTM based tool to automatically punctuate old Hebrew Manuscripts, developed for an education non-profit. image source

Unveiling the Intra-Person Fingerprint Similarity via Deep Contrastive Learning

First ever paper to show intra-person fingerpring similarity. image source

End-to-End Structure Solutions from Information-Compromised Diffraction Data via Generative Deep Learning

A Novel ML approach to Machine Crystalography, using a variational query-based multi-branch deep neural network to predict 3d crystal structure from powder x-ray diffraction.