Type a name, or just describe what you need. Results blend keyword and meaning-based search. 4 matches, each with an EU availability status.
Research · Stanford Hazy Research
Research language-modeling approach that generates text coarse-to-fine, producing tokens in parallel within each stage.
Research
Research method for long-context video generation using hierarchical latents and coarse-to-fine rollout.
Research · Preferred Networks
Generative method from Preferred Networks that reconstructs high-resolution 3D scene meshes from posed multi-view images.
Model
Feed-forward single-image relighting model with physically based light control, using intrinsic conditioning from a coarse 3D scene.
