Context Unrolling in Omni Models
For researchers in multimodal AI, Omni demonstrates a new capability (Context Unrolling) that improves reasoning across diverse modalities, but the novelty is incremental as it builds on existing unified model architectures.
Omni, a unified multimodal model trained on text, images, videos, 3D geometry, and hidden representations, achieves strong performance on multimodal generation and understanding benchmarks by enabling Context Unrolling, which aggregates complementary information across modalities to improve reasoning fidelity.
We present Omni, a unified multimodal model natively trained on diverse modalities, including text, images, videos, 3D geometry, and hidden representations. We find that such training enables Context Unrolling, where the model explicitly reasons across multiple modal representations before producing predictions. This process enables the model to aggregate complementary information across heterogeneous modalities, facilitating a more faithful approximation of the shared multimodal knowledge manifold and improving downstream reasoning fidelity. As a result, Omni achieves strong performance on both multimodal generation and understanding benchmarks, while demonstrating advanced multimodal reasoning capabilities, including in-context generation of text, image, video, and 3D geometry.