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.
Unifies text, images, audio, and video for Chinese-English multimodal understanding and reasoning, with fast instruct and explicit thinking modes. The paper reports leading open-source results on several omni-modal video benchmarks.
Tests multimodal models’ spatial reasoning through screen-based clicks and drags. Its programmatically generated CAPTCHA tasks also form a training environment, with fine-tuning gains reported across seven out-of-distribution benchmarks.