miHoYo's GameScaling study scales embodied game agents from 0.8B to 27B on 1,600 hours of gameplay; models open-sourced on Hugging Face
GameScaling: miHoYo's study on scaling embodied agents in games
Continued pre-training from 0.8B to 27B on 1,600 hours of gameplay across 80 diverse virtual worlds. Models are open-source on Hugging Face.XSources2
- @HuggingPapersXGameScaling: miHoYo's study on scaling embodied agents in games Continued pre-training from 0.8B to 27B on 1,600 hours of gameplay across 80 diverse virtual worlds. Models are open-source on Hugging Face.View original ·
arXivResearchScaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual WorldsView original ·
Headline by dalao.ai. The quoted post is the record; its author keeps authorship.