Xiaomeng Qian (钱晓萌)

I am a first-year PhD student at Fudan University, working with the OpenMOSS team under the supervision of Prof. Xipeng Qiu. Previously, I received my B.Eng. degree from the School of Software, Nanjing University. I conduct my research as a research intern at MOSI Intelligence (模思智能), where the MOSS-VL model family is built.

My research focuses on multimodal video understanding with large foundation models. I am broadly interested in building and improving multimodal foundation models, with the goal of enabling machines to perceive, comprehend, and reason over visual content — particularly in the video domain. My current work explores how to effectively integrate visual and linguistic information to advance video understanding capabilities.

I am a core contributor to the MOSS-VL model family, where I work on training data across the full pipeline — data infrastructure, assembly and delivery, and data synthesis — spanning both pre-training and post-training stages.

News

Aug 15, 2026	We released the MOSS-VL Technical Report, an open vision-language model family for real-time interaction!
Jul 08, 2026	We released MOSS-VL-Realtime, achieving state-of-the-art real-time understanding! Check out our blog.
Apr 08, 2026	We officially released MOSS-VL! Check out our demo.
Mar 02, 2026	Started an internship at MOSI Intelligence, working on the MOSS-VL project.
Jul 01, 2025	Started an internship at the OpenMOSS team, working on MOSS-Video-Preview and MOSS-VL projects.

Selected Publications

arXiv

MOSS-VL Technical Report

Pengyu Wang, Chenkun Tan, Shaojun Zhou, Qirui Zhou, Yanxin Chen, Xingyang He, Huazheng Zeng, Jijun Cheng, Chenghao Wang, Xiaomeng Qian, Pengfei Wang, Zhan Huang, Shanqing Gao, Wei Huang, Longjun Cao, Wu Ran, Jie Liu, Changtai Zhu, Hongkai Wang, Yixian Tian, Chenghao Liu, Zhen Ye, Xinghao Wang, Botian Jiang, Guoguo Feng, Zhaoye Fei, Ruixiao Li, Mingshu Chen, Yang Gao, Qinyuan Cheng, Shimin Li, and Xipeng Qiu

arXiv preprint arXiv:2608.15045, Aug 2026

arXiv Bib

@article{wang2026mossvl,
  title = {MOSS-VL Technical Report},
  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},
  journal = {arXiv preprint arXiv:2608.15045},
  year = {2026},
  month = aug,
  eprint = {2608.15045},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://arxiv.org/abs/2608.15045},
}

arXiv

MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention

Pengyu Wang, Chenkun Tan, Shaojun Zhou, Wei Huang, Qirui Zhou, Zhan Huang, Zhen Ye, Jijun Cheng, Xiaomeng Qian, Yanxin Chen, Xingyang He, Huazheng Zeng, Chenghao Wang, Pengfei Wang, Hongkai Wang, Shanqing Gao, Yixian Tian, Chenghao Liu, Xinghao Wang, Botian Jiang, and Xipeng Qiu

arXiv preprint arXiv:2606.07639, Jun 2026

arXiv Bib

@article{wang2026mossvideo,
  title = {MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention},
  author = {Wang, Pengyu and Tan, Chenkun and Zhou, Shaojun and Huang, Wei and Zhou, Qirui and Huang, Zhan and Ye, Zhen and Cheng, Jijun and Qian, Xiaomeng and Chen, Yanxin and He, Xingyang and Zeng, Huazheng and Wang, Chenghao and Wang, Pengfei and Wang, Hongkai and Gao, Shanqing and Tian, Yixian and Liu, Chenghao and Wang, Xinghao and Jiang, Botian and Qiu, Xipeng},
  journal = {arXiv preprint arXiv:2606.07639},
  year = {2026},
  month = jun,
  eprint = {2606.07639},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://arxiv.org/abs/2606.07639},
}