Welcome to My Blog
RSS FeedA personal blog about technology, machine learning, and other interesting topics. This site follows best practices and provides accessibility out of the box. Light and dark mode are supported by default.
Read the blog posts or check About page for more info.
Featured
-
From Code Points to Subwords: Building a Byte-Level BPE Tokenizer
A walk through tokenization as taught in Stanford's CS336, from Unicode primitives to a full byte-level BPE tokenizer with encode/decode. Covers why UTF-8 wins, how BPE as compression generalizes to language modeling, and the data structures that make the merge loop tractable on a 10GB corpus.
-
From MLE to Variational Inference
A comprehensive exploration of the mathematical progression from maximum likelihood estimation through latent variable models to advanced variational inference techniques, including practical VAE implementations and extensions.
-
From Exponential Complexity to Chain Rules: Understanding Autoregressive Generative Models
A deep dive into the fundamentals of generative modeling, exploring how chain rule factorization solves the curse of dimensionality and enables everything from Bayesian networks to modern Transformers.
Recent Posts
-
RL Series Part 1: A Deep Dive into Policy and Value Iteration
A detailed walkthrough of the foundational model-based RL algorithms, Policy and Value Iteration, grounded in the mathematics of Markov Decision Processes and the Bellman Equation.