New York Site views —Page views —
← All series

Reading paths through AI research

Follow a topic across methods, datasets and the evidence behind a result.

Reading order

  1. Reading Transformer papers: from attention to modern language-model architectures
  2. Reading scaling-law papers: parameters, data, compute and emergent behavior
  3. Reading instruction-tuning papers: supervised fine-tuning and instruction following
  4. Reading preference-optimization papers: reward models, DPO, GRPO and preference data
  5. Reading retrieval-augmented learning papers: from RAG to memory-augmented models
  6. Reading reasoning-model papers: chain of thought, self-consistency, supervision and search
  7. Reading tool-use papers: from ReAct to verifiable tool calls
  8. Reading multimodal LLM papers: vision encoders, alignment data and reasoning
  9. Reading vision-language-action papers: from embodied agents to robotics foundation models
  10. Reading AI for science papers: molecules, proteins, materials and automated experiments
  11. Reading interpretability papers: representations, circuits, probes and causal interventions
  12. Reading safety and alignment papers: red teaming, abstention and controllable generation
  13. Reading evaluation papers: open-ended tasks, human judgments and contamination
  14. Reading data-centric AI papers: selection, deduplication, synthesis and quality
  15. Reading efficient training papers: LoRA, QLoRA, MoE, checkpointing and optimizers
  16. Reading efficient inference papers: KV caching, speculation, quantization and serving
  17. Reading open-model technical reports: model cards, training data, evaluations and limits
  18. Reading rebuttals and peer reviews to assess a paper’s evidence
  19. From ten papers to a research proposal: question, hypothesis, method and experiment
  20. After a month of AI papers: building a lasting reading practice