68 reports across 10 topics
Browse machine learning by topic
Every report is filed under one topic hub, so you can start from a broad area and walk down to the specific papers that shaped it.
Computer vision
Image classification, detection, segmentation, representation learning and neural scene representations.
- computer-vision
- cnn
- object-detection
Architectures
The network designs that mattered: attention, convolutions, residual and graph models, sequence-to-sequence and their descendants.
- transformers
- nlp
- pretraining
Applications & prompting
Reasoning, retrieval and prompting: the techniques that turn a base model into a usable system.
- reasoning
- nlp
- prompting
Efficiency & deployment
Doing more with less compute: adapters, quantisation, fast attention, sparse experts and deployment trade-offs.
- efficiency
- mixture-of-experts
- quantization
Training & data
How models are actually trained — objectives, scaling budgets, regularisation and the data decisions behind the results.
- training
- deep-learning
- regularization
Generative models
Adversarial, diffusion and latent-variable models for synthesising images and other high-dimensional data.
- diffusion
- generative
- generative-models
Reinforcement learning
Agents that learn from reward — value-based methods, policy gradients and self-play.
- reinforcement-learning
- deep-learning
- ppo
Foundations & scaling
Scaling laws, compute-optimal training and the large-model results that reframed what a language model can do.
- scaling-laws
- large-language-models
- training
Alignment & safety
Turning raw predictors into assistants: human feedback, instruction tuning, preference optimisation and self-critique.
- alignment
- rlhf
- human-feedback
Interpretability
What is actually happening inside a trained network, and how we can tell.
- interpretability
- computer-vision
- visualization