About Me

关于我

My name is Feilong Chen (陈飞龙). I was a researcher (Huawei TopMinds, 华为天才少年) at Huawei from 2023 to 2026. I received the Ph.D. degree in Institude of Automation, Chinese Academy of Sciences, under the supervision of Prof. Bo Xu and the B.Sc. degree in computer sciences from Hefei University of Technology.

My research interests include: multimodal large language models, multimodal reasoning, multimodal generation, omni-modal models.

我是陈飞龙，曾任华为“天才少年”（Huawei TopMinds）研究员（2023-2026）。 我于中国科学院自动化研究所获得博士学位，导师为徐波研究员。本科毕业于合肥工业大学。

我的研究兴趣主要集中在： 多模态大语言模型、多模态推理、多模态生成、全模态模型等。

Hiring: 正在招募： I am looking for cooperation or research interns. Contact me if you are interested in the above topics via email at phellon.chen@gmail.com. 我正在寻找合作伙伴或研究实习生。如果你对上述领域感兴趣，欢迎通过邮件联系我：phellon.chen@gmail.com。

Experience

科研经历

2023.07 - 2026.02

Researcher (Huawei TopMinds)

Lead the Research & Development of Multimodal Training Framework on Ascend NPUs, Multimodal Data Construction, and MLLM's Pretraining & Finetuning.

华为 · 研究员 (TopMinds)

主导昇腾 NPU 上的多模态训练框架研发、多模态数据构建及 MLLM 的预训练与微调。

2022.12 - 2023.07

Research Intern @ Huawei Cloud

Mentor: Jianlong Chang, Qi Tian (IEEE Fellow).

华为云 · 研究实习生

导师：常建龙，田奇（IEEE Fellow）。

2021.05 - 2022.03

Research Intern @ Microsoft AI

Mentor: Can Xu.

微软亚洲研究院 · 研究实习生

导师：Can Xu。

2019.04 - 2020.11

Tencent Rhino-Bird Elite Talent @ WeChat AI

Mentor: Fandong Meng.

腾讯微信 AI · 腾讯犀牛鸟精英人才

导师：孟凡东。

Recent News

最近动态

  • 🔥 [2026.03] Release FireRed-OCR Technical Report: A high-performance OCR system.
  • 🚀 [2025.09] Propose MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs.
  • ✨ [2023.05] Release X-LLM: The first Omni-modal large language model.
  • 📚 [2023.01] Publish VLP: The first survey on vision-language pre-training.
  • 🔥 [2026.03] 发布 FireRed-OCR 技术报告：高性能 OCR 系统。
  • 🚀 [2025.09] 提出了 MindVL：面向昇腾 NPU 的高效多模态大模型训练框架。
  • ✨ [2023.05] 发布 X-LLM：首个全模态大语言模型。
  • 📚 [2023.01] 发表 VLP：首篇多模态预训练综述。

Selected Publications

代表性论文

FireRed-OCR
FireRed-OCR Technical Report
H Wu, H Lou, X Li, Z Zhong, Z Sun, P Chen, X Zhou, K Zuo, Y Chen, et al.
arXiv preprint arXiv:2603.01840, 2026
Paper Code Cite
@article{wu2026firered, title={FireRed-OCR Technical Report}, author={Wu, H and Lou, H and Li, X and Zhong, Z and Sun, Z bit and Chen, P and Zhou, X and Zuo, K and Chen, Y and others}, journal={arXiv preprint arXiv:2603.01840}, year={2026} }
MindVL
MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs
Feilong Chen, Y Liu, Y Huang, H Wang, M Tian, YQ Yu, M Liao, J Wu
arXiv preprint arXiv:2509.11662, 2025
Paper Code Cite
@article{chen2025mindvl, title={MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs}, author={Chen, Feilong and Liu, Y and Huang, Y and Wang, H and Tian, M and Yu, YQ and Liao, M and Wu, J}, journal={arXiv preprint arXiv:2509.11662}, year={2025} }
Vilas
Vilas: Exploring the effects of vision and language context in automatic speech recognition
Ziyi Ni*, Minglun Han*, Feilong Chen*, L Meng, J Shi, P Lv, B Xu
ICASSP 2024
Paper Cite
@inproceedings{ni2024vilas, title={Vilas: Exploring the Effects of Vision and Language Context in Automatic Speech Recognition}, author={Ni, Ziyi and Han, Minglun and Chen, Feilong and Meng, Linghui and Shi, Jing and Lv, Pin and Xu, Bo}, booktitle={ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pages={11176--11180}, year={2024}, organization={IEEE} }
X-LLM
X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages
Feilong Chen, Minglun Han, Haozhi Zhao, et al.
Technical Report 2023
Paper Code Cite
@article{chen2023xllm, title={X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages}, author={Chen, Feilong and Han, Minglun and Zhao, Haozhi and Zhang, Qingyang and Shi, Jing and Xu, Shuang and Xu, Bo}, journal={arXiv preprint arXiv:2305.04160}, year={2023} }
MindVL
VLP: A survey on vision-language pre-training
Feilong Chen, Duzhen Zhang, Minglun Han, et al.
Machine Intelligence Research
Paper Cite
@article{chen2023vlp, title={VLP: A survey on vision-language pre-training}, author={Chen, Feilong and Zhang, Duzhen and Han, Minglun and Chen, Xiuyi and Shi, Jing option and Xu, Shuang and Xu, Bo}, journal={Machine Intelligence Research}, volume={20}, number={1}, pages={38--56}, year={2023}, publisher={Springer} }
DualGATs
Dualgats: Dual graph attention networks for emotion recognition in conversations
Duzhen Zhang, Feilong Chen, Xiuyi Chen, et al.
ACL 2023
Paper Cite
@inproceedings{zhang2023dualgats, title={DualGATs: Dual Graph Attention Networks for Emotion Recognition in Conversations}, author={Zhang, Duzhen and Chen, Feilong and Chen, Xiuyi and others}, booktitle={Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, pages={12316--12328}, year={2023} }
ACM MM
Unsupervised and pseudo-supervised vision-language alignment in visual dialog
Feilong Chen, Duzhen Zhang, Xiuyi Chen, Jing Shi, Shuang Xu, Bo Xu
ACM MM 2022
Paper Cite
@inproceedings{chen2022unsupervised, title={Unsupervised and pseudo-supervised vision-language alignment in visual dialog}, author={Chen, Feilong and Zhang, Duzhen and Chen, Xiuyi and Shi, Jing and Xu, Shuang and Xu, Bo}, booktitle={Proceedings of the 30th ACM International Conference on Multimedia}, pages={4142--4153}, year={2022} }
GoG
GoG: Relation-aware graph-over-graph network for visual dialog
Feilong Chen, Xiuyi Chen, Fandong Meng, Peng Li, Jie Zhou
ACL 2021 Findings
Paper Cite
@inproceedings{chen2021gog, title={GoG: Relation-aware graph-over-graph network for visual dialog}, author={Chen, Feilong and Chen, Xiuyi and Meng, Fandong and Li, Peng and Zhou, Jie}, booktitle={Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021}, pages={4112--4123}, year={2021} }
DMRM
DMRM: A Dual-channel Multi-hop Reasoning Model for Visual Dialog
Feilong Chen, Fandong Meng, Jiaming Xu, et al.
AAAI 2020
Paper Code Cite
@inproceedings{chen2020dmrm, title={DMRM: A Dual-Channel Multi-Hop Reasoning Model for Visual Dialog}, author={Chen, Feilong and Meng, Fandong and Xu, Jiaming and others}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence}, volume={34}, number={05}, pages={7468--7475}, year={2020} }

View Google Scholar for full list 查看 Google Scholar 以获取完整列表

Honors & Awards

个人荣誉

  • 2024 CBG President Team Award
  • 2018 Outstanding Undergraduate Student of Anhui Province
  • 2018 Tongze Scholarship (Top 1%)
  • 2015 National Scholarship (Top 1%)
  • 2016 National Endeavor Fellowship (Top 1%)
  • 2024 CBG 总裁团队奖
  • 2018 安徽省优秀毕业生
  • 2018 合肥工业大学“同泽奖学金”（Top 1%）
  • 2015 国家奖学金（Top 1%）
  • 2016 国家励志奖学金（Top 1%）