You Could Have Invented Dr.GRPO Yourself
A ground-up walkthrough of modern RL for LLMs: from REINFORCE to Dr.GRPO, showing how each algorithm was forced by exactly one broken thing in the previous one.
You Could Have Invented Entropy Yourself
A ground-up derivation that runs from a number-guessing game to the loss function of a language model: halving, bits, entropy, cross-entropy, perplexity, and KL divergence, each step the obvious next move from the last.
Does SDFT Survive the Jump to Mixture-of-Experts?
A theory-first investigation: derive the bound that decides whether self-distillation's trust-region guarantee survives in a Mixture-of-Experts, then measure directly where a real 16B MoE lands on it.
Browse the archive
Deep dives & tutorials
Long-form walkthroughs of papers, algorithms, and core ideas in deep learning.
Browse write-ups →Research work
Research projects and theory-first investigations spanning LLMs, fairness, generative modeling, and bio-imaging.
Browse projects →Code & tools
Open source projects, educational toolkits, and code experiments.
Browse repositories →