miHoYo Gamer VLA Analysis: A Vision-Language-Action Agent for Long-Horizon Gaming Tasks

Written by

in

miHoYo’s Honkai AI R&D team has released Gamer, a vision-language-action model that directly outputs keyboard and mouse actions from on-screen visuals, enabling control of long-horizon 3D tasks without relying on game-state APIs.

Source:explainx.ai · Read the original article

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *