SEED - Official Website

SEED is a pioneering group within Electronic Arts, combining creativity with applied research.
We explore, build, and help determine the future of interactive entertainment.

Research & Announcements

EA presents on graphics, gameplay, and generative tech at GDC 2024

Electronic Arts Inc., SEED, Frostbite

Mar 12, 2024

Don’t miss these GDC 2024 talks from Electronic Arts engineers, scientists, and technical artists.

Machine Learning for Game Devs: Part 3

SEED

Jan 16, 2024

An introduction to machine learning for game developers using C++. Part 3: Training a neural network.

SEED’s Voice2Face Honored by Fast Company

SEED

Dec 5, 2023

Electronic Arts and SEED’s Voice2Face project have been named one of Fast Company’s Next Big Things in Tech!

Coverage Bitmasks for Efficient Rendering Algorithms

SEED

Nov 29, 2023

This presentation gives the humble old bitmask the attention it deserves. It discusses where they have been used creatively and where they can be used.

Machine Learning for Game Devs: Part 2

SEED

Nov 16, 2023

A developer-friendly introduction to machine learning using C++. Part 2 of 3: How do you figure out a neural network’s optimal weight and bias values

Machine Learning for Game Devs: Part 1

SEED

Oct 26, 2023

A developer-friendly introduction to machine learning using C++. Part 1 of 3: Understanding and working with a “classic” neural network.

GENEA Challenge 2023: Evaluating Gesture Generation with Two Speakers

SEED

Oct 10, 2023

This paper reports on the third GENEA Challenge, which benchmarks data-driven automatic co-speech gesture generation.

Constant Time Stateless Shuffling and Grouping

SEED

Sep 6, 2023

Stateless shuffling is a technique for shuffling items and arranging them into groups of specific sizes — without actually shuffling or grouping anything.

SEED Applies ML Research to the Growing Demands of AAA Game Testing

SEED

Aug 29, 2023

This year at the IEEE Conference on Games (CoG), SEED researchers presented five papers and a keynote presentation that explored the potential for imitation learning, reinforcement learning, and AI to significantly improve cu…