Teacher since April 2026
Mateo Rojas
Generative models and representation learning, explained with intuition first and maths second
9
tutors built
4.6Sample
average from 20 reviews
335Sample
lessons taught by their tutors
About Mateo
I teach how models learn useful representations and how they generate new data: autoencoders, GANs, diffusion models, self supervised learning and language model pretraining. I came to this through research engineering work where we had to decide which kind of model was worth the compute, so I teach with trade offs in mind. Each topic starts with a picture or a toy dataset you can reason about, and only then do we write down the objective. I also spend real time on evaluation, because generated output is easy to admire and hard to measure, and I would rather you leave sceptical than impressed.
Knows about
Tutors by Mateo
9 tutors
Question answering, from extractive to generative
Understand how QA systems find, read and generate answers, and how to tell when they should abstain56 lessonsSampleMateo Rojas$7GANs: generator versus discriminatorGANs: generator versus discriminator
Understand how adversarial training works, why it is unstable and where GANs still make sense50 lessonsSampleMateo Rojas$8Transfer learning with pretrained modelsTransfer learning with pretrained models
Get strong results from small datasets by starting with a model that has already learned50 lessonsSampleMateo Rojas$5Summarisation systems and their failure modesSummarisation systems and their failure modes
Build and judge summaries that stay faithful to the source, from short notes to long reports46 lessonsSampleMateo Rojas$6How language models are pretrainedHow language models are pretrained
Understand the data, objective, scaling and stability work behind large language model pretraining45 lessonsSampleMateo Rojas$13Autoencoders and latent spacesAutoencoders and latent spaces
Learn how networks compress data into a small code and rebuild it, and what that code is good for44 lessonsSampleMateo Rojas$5Diffusion models from noise to sampleDiffusion models from noise to sample
Understand how diffusion models learn to remove noise and how guidance and latents shape the result44 lessonsSampleMateo Rojas$12Evaluating generated textEvaluating generated text
Measure the quality of generated text with metrics, people and model judges, and know each one's limitsMateo Rojas$8Self supervised and contrastive learningSelf supervised and contrastive learning
Learn how models build useful representations from unlabelled data, and how to test themMateo Rojas$11Recent reviews
What students said about Mateo's tutors.
- Brigid M.Sample
Rigorous and well paced. The sampler lesson could use a bit more on why higher order solvers work, but the practical trade offs were clear.
- Ravi N.Sample
The forger and inspector framing made the training loop easy to remember, and the stabilisation lesson fixed my collapsing face generator.
- Leah G.Sample
Adding unanswerable questions to our test set exposed how often the bot guessed. Practical and honest course.
- Hamid R.Sample
Clear explanation of span prediction and metrics. The multi hop lesson felt a bit short but the decomposition idea worked on my project.
- Thomas B.Sample
Clear, but I was hoping for more hands on code. It is concept focused, which the description does say.
- Mohammed J.Sample
I liked that scaling laws were presented as empirical trends with limits, not magic. The stability lesson matched problems I had seen in smaller runs.