Generative Recommendations: A Mechanistic Guide
A mechanistic deep dive into how generative recommender systems work: from Semantic IDs and RQ-VAE to HSTU, M-FALCON, and production deployment at Meta, Kuaishou, and beyond.
From RMSProp to AdamW: The Optimizer Evolution Story
Tracing the evolution of modern neural network optimizers through the lens of what each was designed to fix: gradient scale heterogeneity, mini-batch noise, and regularization interference.
The Sandwich Framework for Understanding Linear Algebra
Coordinate Translations, Scaling, and State Transitions - A unified approach to linear algebra decompositions