Dynamic language understanding: adaptation to new knowledge in parametric and semi-parametric models

Open-sourcing MuJoCo

From LEGO competitions to DeepMind's robotics lab

Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning

A Generalist Agent

Active offline policy selection

When a passion for bass and brass help build better tools

DeepMind’s latest research at ICLR 2022

An empirical analysis of compute-optimal large language model training

GopherCite: Teaching language models to support answers with verified quotes

Predicting the past with Ithaca

Learning Robust Real-Time Cultural Transmission without Human Data

Probing Image-Language Transformers for Verb Understanding

MuZero’s first step from research into the real world

Red Teaming Language Models with Language Models

Competitive programming with AlphaCode

DeepMind: The Podcast returns for Season 2