Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model

Hoeun Lee; Jaeik Kim; Jusang Oh; Jinhyeok Kim; Geon Choi; Hyeonggeun Kim; Jaeyoung Do

title

authors

Hoeun Lee, Jaeik Kim, Jusang Oh, Jinhyeok Kim, Geon Choi, Hyeonggeun Kim, Jaeyoung Do

date

2026-09-11

venue

arXiv (preprint, not peer reviewed)

arXiv:2609.13053

affiliation

AIDAS Lab

upvotes

9 (Hugging Face Daily Papers, 2026-11-01)

links

abs pdf hf code

primer

Vision-language-action models

abstract

Visual goal and dynamics prediction can provide language-conditioned robot policies with both a target outcome and a representation of action-dependent scene changes. We bring these predictions into action generation and selection through a shared trajectory model. Dynin-Robotics implements this formulation on Dynin-Omni, an omnimodal masked-diffusion backbone, representing language, visual observations, goals, and actions as discrete tokens. By varying conditioning and target spans, the same model learns action prediction, action-conditioned next-observation prediction, terminal goal-state prediction, and trajectory-to-instruction reconstruction. These interfaces support test-time scaling through goal prediction, action-candidate evaluation, and joint refinement of action and future-state predictions. We continually pretrain the model on approximately 1.33 million trajectories from 48 Open X-Embodiment datasets and adapt it separately to downstream domains. On two VLABench tasks, robot pretraining improves adaptation within a fixed Stage-2 step budget, and the full objective mixture improves shifted-instruction success over Policy-only post-training under the same coupled decoder. Combining goal guidance with joint action-next-state denoising further improves shifted-instruction success over action-only decoding; the benefit depends on how the predictions are composed. Dynin-Robotics achieves competitive performance on LIBERO and zero-shot LIBERO-Plus, together with a 78.4% average success rate across four manipulation conditions on a Franka Research 3 robot. An optimized block-parallel implementation accelerates model-side action decoding by up to 29.2x relative to the base implementation under the reported profiling setup. These results support shared trajectory modeling as a common interface for learning complementary robot objectives and composing their predictions during control.

@misc{lee2026dynin,
  title={Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model},
  author={Hoeun Lee and Jaeik Kim and Jusang Oh and Jinhyeok Kim and Geon Choi and Hyeonggeun Kim and Jaeyoung Do},
  year={2026},
  eprint={2609.13053},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2609.13053}
}