Kiyomi Moore

jaebumskiyomi
·

AI & ML interests

LLMs, Machine Learning, Roleplay.

Recent Activity

liked a model 11 days ago
unsloth/Qwen3-4B-GGUF
liked a model 11 days ago
unsloth/Qwen3-30B-A3B-128K-GGUF
liked a model 11 days ago
unsloth/Qwen3-30B-A3B-GGUF
View all activity

Organizations

None yet

jaebumskiyomi's activity

New activity in Delta-Vector/Archaeo-12B-GGUF 3 months ago

My Feedback

👍 1
4
#1 opened 3 months ago by
jaebumskiyomi
reacted to merterbak's post with 🚀 3 months ago
view post
Post
3808
🔥 Meet Muse: that can generate a game environment based on visuals or players’ controller actions. It was developed by Microsoft Research in collaboration with Ninja Theory (Hellblade developer). It’s built on something called the World and Human Action Model (WHAM-1.6B model). They trained on 7 years of Bleeding Edge gameplay and it can generate 2 minute long 3D game sequences with consistent physics and character behaviors all from just a second of input. They’ve gone and open-sourced it too. Open weights, the WHAM Demonstrator, and sample data on Azure AI Foundry for anyone to play with. Hope so soon on Hugging Face 🤗.

📄 Paper: https://www.nature.com/articles/s41586-025-08600-3
Blog Post: https://www.microsoft.com/en-us/research/blog/introducing-muse-our-first-generative-ai-model-designed-for-gameplay-ideation/

  • 1 reply
·