Deep Dives

to remodel a small text-only language model and gift it the ability of vision. This text is to summarize all my learnings, and take a deeper have a look at the network architectures...

is on the core of AI infrastructure, powering multiple AI features from Retrieval-Augmented Generation (RAG) to agentic skills and long-term memory. Consequently, the demand for indexing large datasets is growing rapidly. For engineering...

Why This Piece Exists of the Fourier Transform — more like an intuition piece based on what I’ve learned from it and its application in sound frequency evaluation. The aim here is to construct...

Bayesian statistics you’ve likely encountered MCMC. While the remaining of the world is fixated on the newest LLM hype, Markov Chain Monte Carlo stays the quiet workhorse of high-end quantitative finance and risk...

Abstract datasets are extremely imbalanced, with positive rates below 0.2%. Standard neural networks trained with weighted binary cross-entropy often achieve high ROC-AUC but struggle to discover suspicious transactions under threshold-sensitive metrics. I propose a...

In my latest post, I how hybrid search will be utilised to significantly improve the effectiveness of a RAG pipeline. RAG, in its basic version, using just semantic search on embeddings, will be...

forecasting roughly $50 billion in promoting revenue using econometrics, time-series models, and causal inference. When a senior VP asked how confident we ought to be in a number, I couldn’t hand them a...

dominating the AI debate immediately: that AI goes to interchange all of us, that jobs will disappear inside 18 months, that the collapse of the labor market is inevitable. Some say it with...