AURA: Always-On Understanding and Real-Time Assistance via Video Streams

Home Page

A real-time multimodal streaming system powered by our AURA model, supporting continuous video understanding with speech interaction.

For demo deployment instructions and full source code, please refer to our GitHub repository.

Citation

@article{aura2026,
  title={AURA: Always-On Understanding and Real-Time Assistance via Video Streams},
  author={Lu, Xudong and Bo, Yang and Chen, Jinpeng and Li, Shuhan and Guo, Xintong and Guan, Huankang and Liu, Fang and Xu, Dunyuan and Sun, Peiwen and Sun, Heyang and Liu, Rui and Li, Hongsheng},
  journal={arXiv preprint arXiv:2604.04184},
  year={2026}
}
Downloads last month
11
Safetensors
Model size
770k params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for aurateam/AURA

Finetuned
(222)
this model

Paper for aurateam/AURA