Skip to main contentSkip to navigation
P
Portfolio

Projects &
Research

17 projects across 7 years — spanning published research, live products, ML systems, and hardware builds.

17Projects
2Published papers
3Live / installable
7+Years
Filter
Sort

Showing 17 of 17 projects

ProjectResearch
2026

Personalized Preparation in Early Autism Intervention

Clinical Trial · Maya Care and Grow · Agartala

Personalized Preparation in Early Autism Intervention

Hierarchical Bayesian adaptive N-of-1 randomized crossover trial identifying the optimal pre-session warm-up (Stimulating, Calming, Child-Led, or None) for each child with autism.

RStanbrms
Live ProductWeb App
2025

Compass — Platform for Intentional Human Connections

Founder & Maintainer

Compass — Platform for Intentional Human Connections

Free, open-source platform to help people form deep connections — platonic, romantic, or collaborative. Keyword search, transparent database, no ads, no hidden algorithms.

TypeScriptReactNext.js
600+ members
Published PaperResearch
2021

Greedy Decentralized Auction-based Task Allocation

Graduate Research · UT Austin

Greedy Decentralized Auction-based Task Allocation

Greedy Coalition Auction Algorithm (GCAA) assigning hundreds of agents to thousands of tasks in real time — applications in aerial firefighting, ride-sharing, and warehouse robotics. One task assigment per auction phase; faster than traditional auction algorithms.

MATLABPython
70 citations
Master's ThesisHardware
2020

Design of a Smart Sensor for Bird Detection

Master's Thesis · UCLouvain

Design of a Smart Sensor for Bird Detection

Ultra-low-power audio IoT sensor harvesting solar energy via supercapacitor. Runs a KNN classifier on-device to discriminate four Belgian bird species at 94% precision. 15+ year lifetime, LoRaWAN communication.

CEmbeddedLoRaWAN
94% accuracy
ProjectML / AI
2025

AI Agent for Squadro Board Game

Personal Project

AI Agent for Squadro Board Game

AlphaZero variant using MCTS improved by a policy-value CNN trained purely by self-play. Includes Elo tracking, experience replay, and cosine-annealed learning rate.

PythonPyTorch
Outperforms Humans
Live ProductWeb App
2023

Youtube AdBlock

Firefox Extension

Youtube AdBlock

Firefox add-on that accelerates and skips YouTube ads in under two seconds. Prioritizes user security by operating entirely within the local browser environment without collecting data or storing external cookies.

JavaScript
6500+ users
Published PaperResearch
2022

Collision Avoidance for Moving Obstacles

Graduate Research · UT Austin

Collision Avoidance for Moving Obstacles

Local motion planning for agents navigating around moving elliptical obstacles with time-varying shape, bounded environments, and limited control input. 2D and 3D simulations.

MATLAB
17 citations
ProjectML / AI
2021

Reinforcement Learning for Cooperative Manipulation

Project in Robot Learning · UT Austin

Reinforcement Learning for Cooperative Manipulation

DDPG agent with Hindsight Experience Replay (HER) for robotic manipulation tasks. Demonstrated on OpenAI Fetch pick-and-place and Robosuite two-arm lifting.

PythonPyTorch
ProjectHardware
2019

Building of Astrobee

Space Systems Laboratory · MIT

Building of Astrobee

Built the avionics of NASA's Astrobee robot (ISS crew assistant) during a UCLouvain–MIT exchange. Designed avionics diagrams, sourced components, soldered PCBs, and tested sensors and development boards.

ElectronicsPCB Design
ProjectHardware
2019

Design of a Wheeled Driving Robot

Project in Mechatronics · UCLouvain · Eurobot

Design of a Wheeled Driving Robot

Fully autonomous robot for the Eurobot contest. Implemented path planning (potential fields), Kalman-filtered LIDAR localisation, low-level wheel control, and an Android Wi-Fi remote — running on Raspberry Pi + FPGA.

C++SystemVerilogFPGA
2nd place Belgium
Live ProductWeb App
2024

Login Bypasser

Firefox Extension

Login Bypasser

Firefox add-on that removes login popups and access banners from social media and news sites (Facebook, LinkedIn, Instagram), letting you read content without an account.

JavaScript
1600+ users
ProjectML / AI
2024

Large Language Models from Scratch

Personal Project

Large Language Models from Scratch

Full transformer implementation including encoding, embedding, multi-head attention, and MLP layers. Trains an LLM of any size on arbitrary text, and fine-tunes GPT-2 on custom corpora for text generation.

PythonPyTorch
Full Transformer Implementation
ProjectML / AI
2024

Cellular Automata

Reproduction of Fundamental Computer Systems #1

Cellular Automata

Classic 1-D and 2-D cellular automata including Conway's Game of Life and Wolfram's Rule 110. Demonstrates how complex biological processes emerge from simple local rules.

Python
ProjectML / AI
2022

Convolutional Neural Network for Digit Recognition

ML / AI Series #1

Convolutional Neural Network for Digit Recognition

Handwritten digit recognition using a CNN trained on the MNIST dataset. The model processes images through feature extraction and a multilayer perceptron to output the most likely digit.

PythonPyTorchTorchvision
95% accuracy
ProjectResearch
2022

Multi-Agent Motion Planning with Military Maps

Graduate Research · UT Austin · Army Research Lab

Multi-Agent Motion Planning with Military Maps

Dijkstra-based path planning over military terrain — obstacles, elevation, and valence maps. Runs a fast global route over a downsampled mesh, then refines only the next executed segment at full resolution, cutting compute time significantly without sacrificing local path quality.

Python
ProjectResearch
2021

Covariance Steering Games with Wasserstein Distance

Project in Multi-Agent Systems · UT Austin

Covariance Steering Games with Wasserstein Distance

Two algorithms for discrete-time linear covariance steering dynamic games. Iterative best response and LQG reformulation via Riccati equations, evaluated on convergence and solution quality.

Python
ProjectML / AI
2019

Prediction of Air Quality in Beijing

Project in Machine Learning · UCLouvain

Prediction of Air Quality in Beijing

PM2.5 concentration prediction using regression models on meteorological data. Covers feature selection (Mutual Information), extraction (PCA), error estimation (Bootstrap 632), and Neural Network / KNN / Lasso / tree models.

PythonPyTorchSklearn