6 paths · 42 curated steps
Guided paths through the literature
Each path is an ordered route through the reports: start with the paper that introduced the idea, then follow the line to what people use today.
The Transformer lineage
Start with the attention mechanism, meet the original Transformer, then follow the line through BERT, GPT-3, T5, RoBERTa, vision transformers, rotary embeddings and the move away from attention with Mamba and sparse mixture-of-experts.
5 stepsAligning models with humans
How raw next-token predictors became assistants: reinforcement learning from human preferences, instruction tuning, constitutional AI, direct preference optimization and self-critique loops.
5 stepsGenerative image models
From adversarial training to score-based diffusion and latent synthesis, plus the representation learning and scene models that made controllable generation possible.
8 stepsComputer vision, AlexNet to SAM
How deep networks took over image understanding: the convolutions that started it, residual connections that made depth trainable, the transformer and contrastive turns, real-time detection, segmentation and neural scene representations.
5 stepsTeaching models to reason
Prompting as a reasoning interface: chain-of-thought, self-consistency, tool-using ReAct agents and deliberate search over thoughts.
8 stepsMaking models cheap to run
Scaling laws and compute-optimal training set the budget; adapters, quantization, flash attention and sparse experts decide how it is spent at inference time.