LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model
We present \textbf{LLaDA-o}, an effective and length-adaptive omni diffusion model for multimodal understanding and generation. LLaDA-o is built on a Mixture of Diffusion (MoD) framework that decouples discrete masked diffusion for text understanding and continuous diffusion for visual generation, while coupling them through a shared, simple, and efficient attention backbone that reduces redundant computation for fixed conditions. Building on MoD, we further introduce a data-centric length adaptation strategy that enables flexible-length decoding in multimodal settings without architectural changes. Extensive experiments show that LLaDA-o achieves state-of-the-art performance among omni-d...
| Authors | Zebin You, Xiaolu Zhang, Jun Zhou et al. |
|---|---|
| Primary category | cs.CV |
| Published | 1 March 2026 |
| Last updated at source | 1 March 2026 |
Connected in the knowledge graph
- GSAI-ML/LLaDA-VModel · cited by
Models and datasets referencing this paper
- GSAI-ML/LLaDA-VModel
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.