Flashcards

2,671 cards in 36 decks, written from the same source as the concepts. Space to flip, arrows to move, K and R to sort what you know from what you do not. Progress lives in your browser.

All decks 01Foundations 02Transformer Internals 03Training & Fine-Tuning 04Reinforcement Learning 05Inference, Systems & Hardware 06Applied LLM Engineering 07Reasoning, Evaluation & Safety 08Multimodal & Applications

Multimodal & Applications

Beyond text — vision, speech, robotics and scientific discovery.

5decks

395cards

Vision & Multimodal

ViT, CLIP, diffusion, SAM, and the vision-language models that read images as tokens.

32 cards 6 concepts

Speech Recognition

Spectrograms, CTC, RNN-T, Conformer, Whisper, streaming, diarisation and self-supervised audio.

140 cards 20 concepts

Speech Synthesis

Acoustic models and vocoders, Tacotron, FastSpeech, HiFi-GAN, neural codecs and voice cloning.

139 cards 20 concepts

Robotics & Embodied AI

Vision-language-action models, action tokenisation, diffusion policies and sim-to-real.

32 cards 5 concepts

AI for Science

AlphaFold, protein language models, materials discovery, and the pitfalls of ML-for-science.

52 cards 9 concepts