Dynin-Omni: Omnimodal Unified Large Diffusion Language Model
We present Dynin-Omni, the first masked-diffusion-based omnimodal foundation model that unifies text, image, and speech understanding and generation, together with video understanding, within a single architecture. Unlike autoregressive unified models that serialize heterogeneous modalities, or compositional unified models that require orchestration with external modality-specific decoders, Dynin-Omni natively formulates omnimodal modeling as masked diffusion over a shared discrete token space, enabling iterative refinement under bidirectional context. Dynin-Omni adopts a multi-stage training strategy with model-merging-based modality expansion and omnimodal alignment. We evaluate Dynin-O...
| Authors | Jaeik Kim, Woojin Kim, Jihwan Hong et al. |
|---|---|
| Primary category | cs.CL |
| Published | 9 March 2026 |
| Last updated at source | 9 March 2026 |
Popularity, last 2 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- snu-aidas/Dynin-OmniModel · cited by
Models and datasets referencing this paper
- snu-aidas/Dynin-OmniModel
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.