MolmoAct2: Action Reasoning Models for Real-world Deployment Paper • 2605.02881 • Published 2 days ago • 178
Nano-World-Model Collection 🌍 A minimalist repository for training video world models based on diffusion-forcing. • 18 items • Updated 1 day ago • 5
Nano-World-Model Collection 🌍 A minimalist repository for training video world models based on diffusion-forcing. • 18 items • Updated 1 day ago • 5
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Paper • 2604.24763 • Published 9 days ago • 68
Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising Paper • 2604.26694 • Published 7 days ago • 6
Nano-World-Model Collection 🌍 A minimalist repository for training video world models based on diffusion-forcing. • 18 items • Updated 1 day ago • 5
Nano-World-Model Collection 🌍 A minimalist repository for training video world models based on diffusion-forcing. • 18 items • Updated 1 day ago • 5