19PINE-AI/latent-bridge-games
A learned continuous slow→fast latent channel for real-time game agents: frozen MiniCPM-o 4.5 (fast) + Qwen3-VL-8B-Thinking (slow), 33M-param bridge. The latent helps iff slow reasoning helps (T>F). Paper: arXiv:2606.24470
ORIGINAL REPOSITORY
19PINE-AI/latent-bridge-games ↗GitHub activity
- Stars
- 5
- Forks
- 0
- Open issues and PRs
- 1
- Repository size
- ~80,366 KB
- Default branch
- main
- Created
- May 15, 2026
- Repository updated
- Sep 20, 2026
- Last push
- Jun 29, 2026
- Language
- Python
- License
- MIT
Topics agents · arcade-learning-environment · atari · deep-learning · fast-slow · game-ai · llava · llm · machine-learning · multimodal · pytorch · real-time
Repository-wide figures from GitHub, checked Nov 6, 2026. Stars are endorsements, not a Mega AI Hub quality rating. Repository size is GitHub’s estimate; a ZIP download may differ.
Resource information
- Original repository
- 19PINE-AI/latent-bridge-games
- Credit basis
- GitHub repository owner or organization; individual authorship is not asserted
- Publisher
- 19PINE-AI
- Upstream last modified
- Sep 20, 2026
- Official website
- https://github.com/19PINE-AI/latent-bridge-games
- Languages
- Python
- Access
- Open original GitHub repository; publisher terms apply
- Last checked
- Nov 6, 2026
- License
- MIT
- Last record update
- Nov 6, 2026