Official Implementation of Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agents
Like RainBowLuoCS/Gamer, 0 likes 0 Bookmark RainBowLuoCS/Gamer, 0 bookmarks 0 Scaling in Games: Continued Pre-Training for Embodied Agents in Diverse Virtual Worlds. Weights on Hugging Face.
Like THUSI-Lab/GameScaling, 0 likes 0 Bookmark THUSI-Lab/GameScaling, 0 bookmarks 0 [ICML 2026] GameVerse: Can Vision-Language Models Learn from Video-based Reflection?
Like THUSI-Lab/GameVerse, 0 likes 0 Bookmark THUSI-Lab/GameVerse, 0 bookmarks 0 A Foundation Model for Generalist Gaming Agents
Like MineDojo/NitroGen, 0 likes 0 Bookmark MineDojo/NitroGen, 0 bookmarks 0 An agent skill that plays ARC-AGI-3. One rule: say what an action will do before you spend it. Claude Code on Opus 5 finished all 25 public games at 100.00 RHAE in 7,645 actions.
Like pbshgthm/arc-skill, 0 likes 0 Bookmark pbshgthm/arc-skill, 0 bookmarks 0 FLUX 3 Action: open weights 7B world action model from Black Forest Labs. Train, fine-tune and run action prediction for robots (DROID, SO-101), simulators and games.
Like black-forest-labs/flux-action, 0 likes 0 Bookmark black-forest-labs/flux-action, 0 bookmarks 0 GameWAM: A World Action Model for Video Games
Like yunncheng/GameWAM, 0 likes 0 Bookmark yunncheng/GameWAM, 0 bookmarks 0 A Controlled Laboratory for Vision-Language-Action Policy Research
Like Chaoqi-LIU/praxis-vla, 0 likes 0 Bookmark Chaoqi-LIU/praxis-vla, 0 bookmarks 0