arXiv · 2025 · Preprint

DeepOmni: Towards Seamless and Smart Speech Interaction with Adaptive Modality-Specific MoE

Hang Shao, Heting Gao, Yunhang Shen, Jiawei Chen, Zuwei Long, Dong Yang, Ke Li, Xing Sun

Rendered by arXiv from the LaTeX source. If anything looks wrong, switch to the PDF.HTML · PDF · Open in a new tab ↗ · Close
Date
2025-06-27
Citations
1
arXiv
2506.21864
Cite
@misc{shao2025deepomni,
  title = {DeepOmni: Towards Seamless and Smart Speech Interaction with Adaptive Modality-Specific MoE},
  author = {Hang Shao and Heting Gao and Yunhang Shen and Jiawei Chen and Zuwei Long and Dong Yang and Ke Li and Xing Sun},
  year = {2025},
  eprint = {2506.21864},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.21864},
}