New

The ML Engineer’s

Cookbook

2026 Edition

52 recipes — GRPO, Flow Matching, World Models, and everything in between

A cookbook of modern training methodologies for AI engineers who build. Centered on the recipes that actually matter right now — spanning 7 domains — with pipeline diagrams, compute estimates, and paper references.

Free PDF · No spam · 90+ pages

GRPODAPOOn-Policy DistillationRLVRFlow MatchingWorld ModelsTool-Use RL
Contents

What’s Inside

Part 01

Language Models

12 recipes progressing from reward-based RL methods (GRPO, DAPO, RLVR) through alignment techniques (Preference Optimization, Constitutional AI, Process Supervision) to self-improving systems (Recursive Self-Improvement, Synthetic Curriculum, Interaction Models) and alternative architectures (State-Space Models, Linear Attention).

12 recipes

Part 02

Vision

7 recipes covering the shift from diffusion-based generation to flow matching and rectified flow, with preference optimization for visual quality, reward-guided fine-tuning, and self-training loops for continuous improvement.

7 recipes

Part 03

3D Generation

8 recipes spanning multi-view diffusion, Gaussian splatting supervision, mesh generation, neural field training, scene-level generation, world-state prediction, synthetic 3D pretraining, and animation distillation — one of the fastest-moving areas with few consolidated references.

8 recipes

Part 04

Speech

5 recipes tracing the arc from self-supervised speech tokenization (HuBERT, EnCodec) through codec language models (VALL-E, AudioLM) to speech RL fine-tuning, multi-speaker distillation, and few-shot voice cloning.

5 recipes

Part 05

Robotics

7 recipes from latent world models (Dreamer) and action diffusion through sim-to-real transfer, behavior cloning, offline RL, and interactive correction loops — covering the full training stack for embodied AI.

7 recipes

Part 06

Agents

7 recipes building from tool-use RL through web agents and computer-use models, memory optimization, skill distillation, hierarchical planning, and multi-agent coordination — the practical training stack for deploying LLM agents.

7 recipes

Part 07

Synthetic Data

7 recipes covering the full synthetic data pipeline: self-instruction, evolutionary expansion, constrained generation, judge/critic training, quality filtering, curriculum synthesis, and production data flywheels for continuous improvement.

6 recipes

Format

Every Recipe, One Format

Instead of summarizing papers, each recipe extracts the training methodology: the problem it solves, the pipeline, architecture decisions, compute requirements, and where it works best.

Sample Recipe★★★★

On-Policy Distillation

Thinking MachinesFrontier reasoning models

Instead of learning from teacher answers, let the student generate responses and have the teacher correct those trajectories.

Training Pipeline

TeacherStudent RolloutTeacher CorrectionsLossRepeat

Get Your Free Copy

52 training recipes with pipeline diagrams, compute estimates, and paper references. Delivered as a PDF to your inbox.

Free PDF · No spam · 90+ pages