Writing
Blog
Interactive tools, long-reads, and deep dives into ML, GPU architecture, and inference
RL for Diffusion Models: Part 2
Reward models for diffusion RL: annotation, yes/no checklists, VLM judges, agentic critics, and balancing several rewards in one advantage (GDPO, GD²PO, DAPO).
October 2026 · ~27 min read · RU/ENRL for Diffusion Models: Part 1
How to deliver a reward to a diffusion model: gradients through the trajectory (ReFL, DRaFT, DRTune, ShortFT) and online policy gradient (Flow-GRPO, DiffusionNFT, AWM).
October 2026 · ~20 min read · RU/ENDirect Preference Optimization (DPO) for Diffusion Models
Teaching visual preferences to diffusion models: DPO pairs, FiFA, and training without losing generation quality.
July 2026 · ~15 min read · RU/ENAge of Autoresearch
Expertise moves from "find the solution" to "build the system that finds it". Oracles, loops, pitfalls — and what remains for the human.
March 2026 · ~20 min readGPU Story: from triangles to AI chips
How a triangle-drawing chip became the most important processor on the planet. GPU history from first principles — parallelism, shaders, CUDA, Tensor Cores, and what comes next.
March 2026 · Interactive toolReal-Time Video Generation Calculator
First-principles compute estimator for diffusion and AR streaming video models. Adjust model size, steps, VAE compression, sparse attention, hardware, and precision to see if realtime generation is achievable.