Technical Blogs

Scribbles and Notes


Explainable AI (XAI) and Model Interpretability (SHAP, Integrated Gradients, and Sparse Autoencoders)

A future-me-friendly toolbox of interpretability methods: feature attribution (Shapley/SHAP, Integrated Gradients), perturbation tests, and representation-level methods like Sparse Autoencoders.

9 min read   ·   2026

Diffusion Language Models Deep Dive (Part 1: Method)

This post explains general development of diffusion language models (DLMs), including Discrete Diffusion, and Simple and Effective Masked Diffusion Language Models.

6 min read   ·   2026

Minimum Math Review for Diffusion Language Models

Diffusion Objective, Variational Inference, and KL

10 min read   ·   2026

More on Parallelism

More on Sharding and Parallelism

5 min read   ·   2026

Transformer, Scaling, and Efficiency

Summary Notes on Catching Up

7 min read   ·   2025