Blog

Notes on generative AI, anomaly detection, benchmarking, and the occasional math.

2026-06-21 · 7 min read

Demystifying Variational Autoencoders (VAEs): From Variational Inference to Deep Generative Models

A from-scratch walkthrough of the math behind VAEs — from ELBO and KL divergence to the reparameterization trick — explained the way I wish someone had explained it to me.

VAEgenerative-modelsdeep-learningvariational-inference
2024-11-20 · 2 min read

AI-Sciantist: An Autonomous Research Loop That Never Sleeps

I built a closed-loop AI research system that ideates, implements, trains, evaluates, and iterates on ML experiments — with 8 expert personas, HPC cluster integration, and live human steering.

projectAIautonomous-researchLLM
2024-09-15 · 2 min read

Paper Reader: Listening to Science, One Word at a Time

How I built a web app that reads scientific papers aloud with word-level highlighting, converts LaTeX math to spoken English, and runs on Kubernetes with neural TTS.

projectTTSpaper-readeraccessibility
2024-06-19 · 2 min read

Variational Autoencoders for Anomaly Detection: A Gentle Introduction

A walkthrough of how variational autoencoders can be used for unsupervised anomaly detection, with the math behind the ELBO and reconstruction-based scoring.

VAEanomaly detectiongenerative models
2024-03-10 · 1 min read

Running the MOOD Challenge: Lessons from 80+ Teams

Five years of organizing an international anomaly detection benchmark taught me a lot about fair evaluation, Docker-based submissions, and what really matters in medical AI.

benchmarkingOODMOODevaluation