Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

Python programs, usually short, of considerable difficulty, to perfect particular skills.

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Solve puzzles. Learn CUDA.

Zero-Shot Speech Editing and Text-to-Speech in the Wild

A course on aligning smol models.

Structured state space sequence models

Rainbow is all you need! A step-by-step tutorial from DQN to Rainbow

Implementation of all RL algorithms in a simpler way

The repository is for safe reinforcement learning baselines.

RLeXplore provides stable baselines of exploration methods in reinforcement learning, such as intrinsic curiosity module (ICM), random network distillation (RND) and rewarding impact-driven explora…

This is a collection of the code that accompanies the reports in The Gallery by Weights & Biases.

A BERT that you can train on a (gaming) laptop.

Repository for theory and methods for Out-of-Distribution (OoD) generalization

Explore XAI in ML with Jupyter Notebooks: This repo offers practical demonstrations of various Explainable AI techniques like Counterfactuals, SHAP, and more, suited for diverse applications in fie…

Code for our AAAI 26 paper: "Expressive Temporal Specifications for Reward Monitoring"

Learn how to model and solve combinatorial problems using Reinforcement Learning. Provided as a ReCoDE Exemplar by Imperial College London.