LEARNING PATH · AI Engineering

The Papers Bootcamp

For engineers who want to read the canonical deep-learning papers in the right order.

Advanced ~5h 30m22 lessons22 steps

The papers that built modern AI, sequenced so each one earns the next — from word2vec and the Transformer through scaling laws, RLHF, chain-of-thought, RAG, LoRA and MoE, out to vision and diffusion. Every entry is a plain-English breakdown, not the raw PDF.

  • Read the canonical papers in a coherent, building order
  • Connect each paper to the capability it unlocked
  • Trace the line from word vectors to reasoning models
  • Follow the field beyond language into vision and diffusion
0 / 22 done · 0%
  1. Paper BreakdownNext up

    Word2Vec

    Distributed word representations — the seed.

  2. Paper Breakdown

    Seq2Seq

    Encoder–decoder sequence learning.

  3. Paper Breakdown

    Attention Is All You Need

    The Transformer.

  4. Paper Breakdown

    BERT

    Bidirectional pretraining — the encoder line.

  5. Paper Breakdown

    GPT-3

    Few-shot learning at scale — the decoder line.

  6. Paper Breakdown

    Scaling Laws

    Why scale works, quantified.

  7. Paper Breakdown

    Chinchilla

    Compute-optimal training — data matters as much as size.

  8. Paper Breakdown

    InstructGPT

    Alignment via human feedback — RLHF.

  9. Paper Breakdown

    Chain-of-Thought Prompting

    Let models think step by step.

  10. Paper Breakdown

    Self-Consistency

    Sample many chains of thought, then vote.

  11. Paper Breakdown

    Retrieval-Augmented Generation

    Ground generation in retrieval.

  12. Paper Breakdown

    LoRA

    Fine-tune cheaply — low-rank adapters.

  13. Paper Breakdown

    Direct Preference Optimization

    Alignment without a separate reward model.

  14. Paper Breakdown

    Mixture of Experts

    Scale parameters without scaling compute.

  15. Paper Breakdown

    FlashAttention

    Make attention IO-aware and fast.

  16. Paper Breakdown

    ReAct

    Interleave reasoning and acting — agents.

  17. Paper Breakdown

    Toolformer

    Teach a model to call tools.

  18. Paper Breakdown

    DeepSeek-R1

    Reasoning that emerges from reinforcement learning.

  19. Paper Breakdown

    Vision Transformer (ViT)

    Transformers leave language — ViT.

  20. Paper Breakdown

    CLIP

    Connect images and text.

  21. Paper Breakdown

    Diffusion Models

    The generative engine behind modern image models.

  22. Paper Breakdown

    Whisper

    Weakly-supervised speech recognition at scale.

← All learning paths