Evaluates whether GUI agents can locate interface elements from Korean instructions and website screenshots. Its 3,319 human-annotated examples span 142 websites, providing a focused test of visual grounding on Korean web interfaces.
Turns photos into detailed foreground alpha mattes, with particular attention to hair, fur, shadows, and complex edges. Built on a generative image-editing model and distilled to four steps; self-hosted weights are non-commercial only and require substantial GPU memory.
Scales verifiable gameplay data by having a Builder and visual and coding players co-develop web games. Progress-weighted training improves agent performance on both its own benchmark and an external game benchmark.
Enables interactive world models to follow user-defined rules and preserve them across save-and-restore. An executable 3D rule graph tracks rules, dependencies, and object states, while constraining video generation to show their effects.
Generates images in a single forward pass and handles image-to-image tasks and dense prediction with the same model. A shared random state coordinates image codes for global coherence; 512×512 generation takes about 78 ms on an H200.