Video-Text-to-Text
Transformers
Safetensors
English
Chinese
moss_vl
feature-extraction
Realtime
Streaming
Video-Understanding
Image-Understanding
MOSS-VL
OpenMOSS
multimodal
video
vision-language
custom_code
Instructions to use OpenMOSS-Team/MOSS-VL-Realtime with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMOSS-Team/MOSS-VL-Realtime with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenMOSS-Team/MOSS-VL-Realtime", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -27,6 +27,10 @@ tags:
|
|
| 27 |
|
| 28 |
# MOSS-VL-Realtime
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
## Overview
|
| 31 |
|
| 32 |
MOSS-VL-Realtime is the realtime streaming checkpoint of the MOSS-VL release, part of the OpenMOSS ecosystem for open visual understanding.
|
|
@@ -366,11 +370,23 @@ We are continuing to improve realtime response timing, dynamic correction, broad
|
|
| 366 |
## Citation
|
| 367 |
|
| 368 |
```bibtex
|
| 369 |
-
@misc{
|
| 370 |
-
title = {
|
| 371 |
-
author = {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 372 |
year = {2026},
|
| 373 |
-
|
| 374 |
-
|
|
|
|
|
|
|
| 375 |
}
|
| 376 |
```
|
|
|
|
| 27 |
|
| 28 |
# MOSS-VL-Realtime
|
| 29 |
|
| 30 |
+
MOSS-VL is an open vision-language model family from OpenMOSS, supporting image understanding, long-video understanding, and realtime streaming interaction.
|
| 31 |
+
|
| 32 |
+
**Technical Report**: [https://arxiv.org/pdf/2608.15045](https://arxiv.org/pdf/2608.15045)
|
| 33 |
+
|
| 34 |
## Overview
|
| 35 |
|
| 36 |
MOSS-VL-Realtime is the realtime streaming checkpoint of the MOSS-VL release, part of the OpenMOSS ecosystem for open visual understanding.
|
|
|
|
| 370 |
## Citation
|
| 371 |
|
| 372 |
```bibtex
|
| 373 |
+
@misc{mossvl,
|
| 374 |
+
title = {MOSS-VL Technical Report},
|
| 375 |
+
author = {Wang, Pengyu and Tan, Chenkun and Zhou, Shaojun and Zhou, Qirui and Chen, Yanxin and He, Xingyang and Zeng, Huazheng and Cheng, Jijun and Wang, Chenghao and Qian, Xiaomeng and Wang, Pengfei and Huang, Zhan and Gao, Shanqing and Huang, Wei and Cao, Longjun and Ran, Wu and Liu, Jie and Zhu, Changtai and Wang, Hongkai and Tian, Yixian and Liu, Chenghao and Ye, Zhen and Wang, Xinghao and Jiang, Botian and Feng, Guoguo and Fei, Zhaoye and Li, Ruixiao and Chen, Mingshu and Gao, Yang and Cheng, Qinyuan and Li, Shimin and Qiu, Xipeng},
|
| 376 |
+
year = {2026},
|
| 377 |
+
eprint = {2608.15045},
|
| 378 |
+
archivePrefix = {arXiv},
|
| 379 |
+
primaryClass = {cs.CV},
|
| 380 |
+
url = {https://arxiv.org/abs/2608.15045}
|
| 381 |
+
}
|
| 382 |
+
|
| 383 |
+
@misc{mossvideopreview,
|
| 384 |
+
title = {{MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention}},
|
| 385 |
+
author = {Pengyu Wang and Chenkun Tan and Shaojun Zhou and Wei Huang and Qirui Zhou and Zhan Huang and Zhen Ye and Jijun Cheng and Xiaomeng Qian and Yanxin Chen and Xingyang He and Huazheng Zeng and Chenghao Wang and Pengfei Wang and Hongkai Wang and Shanqing Gao and Yixian Tian and Chenghao Liu and Xinghao Wang and Botian Jiang and Xipeng Qiu},
|
| 386 |
year = {2026},
|
| 387 |
+
eprint = {2606.07639},
|
| 388 |
+
archivePrefix = {arXiv},
|
| 389 |
+
primaryClass = {cs.CV},
|
| 390 |
+
url = {https://arxiv.org/abs/2606.07639}
|
| 391 |
}
|
| 392 |
```
|