Writing

Currently, my technical writing is mainly hosted on Medium. Below is a list of topics I covered so far.

Reinforcement Learning for Reasoning Tasks

• Generate Once, Train Many: Implementing GRPO’s Efficient Sampling from Scratch

• Beyond generate(): A Deep Dive into Stateful, Multi-Turn LLM Rollouts for Tool Use

• The Evolution of Policy Optimization: Understanding GRPO, DAPO, and Dr. GRPO’s Theoretical Foundations

• Bridging Theory and Practice: Understanding GRPO Implementation Details in Hugging Face’s TRL Library

Optimizer

• Going Beyond AdamW: A Practical Guide to the Muon Optimizer

Distributed Computing

• The “Turtle Speed” Breakthrough 🐢✨, Part 3: My Map of the Distributed Nightmare

• The “Turtle Speed” Breakthrough 🐢✨ Part 2: The Blueprint for Distributed Chaos

• The “Turtle Speed” Breakthrough 🐢✨: Decoding Distributed Optimizers from FSDP to Muon’s Secret Sauce

• No-BS Glossary: Distributed Training 🚀 + The WHY Behind The How

Engineering Best Prqctices

• A Single Function, A World of Engineering: Deep Dive into Memory-Efficient Token Probability Calculation in Hugging Face TRL

AI Ethics

• When “Safety” Feels Like Gaslighting: My Experience With Claude

I also cover cutting edge mahine learning research papers for the Batch from

DeepLeaning AI

• 10 Million Tokens of Input Context

• Better Spatial Perception for Robots