New AI Model Can Recreate Super Mario Bros. Footage, But It's Full Of Glitches

Let's-a not!

Researchers from tech company Virtuals Protocol have published a paper on a new text-to-video AI model, MarioVGG, which can simulate Super Mario Bros. footage via some basic text inputs (thanks, ArsTechnica).

The model was fed over 737,000 Mario Bros. frames, showing Nintendo's prized plumber in 32 different levels with varying degrees of success and failure (141 wins and 139 losses, according to Github). Based on these images, and how they are arranged, the AI model "learns" what commands such as "jump" and "run" correspond to on-screen and is then capable of simulating such commands in a video format, physics and all.

Read the full article on nintendolife.com

from Nintendo Life | Latest Updates https://ift.tt/Q0kUiHG

Share on Google Plus

About Unknown

This is a short description in the author block about the author. You edit it by entering text in the "Biographical Info" field in the user admin panel.