My name is Feilong Chen (陈飞龙). I am currently a researcher (Huawei TopMinds, 华为天才少年) at Huawei. My research interests include (Native) multimodal large language models, multimodal reasoning, multimodal generation, omni-modal models. See my Google scholar for more details.

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.

Hiring

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 or feilong.chen@huawei.com .

Recent News

We propose MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs. Notably, despite using about 1/10 of the training data required by Qwen2.5-VL, MindVL achieves performance on par with Qwen2.5-VL in evaluations of general multimodal understanding and document/table comprehension. Beyond overall scores, MindVL also delivers leading performance in OCR assessments.
The fisrt Omni-modal large language model: ‘‘X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages’’
The first suvery on vison language pretraining: ‘‘VLP: A survey on vision-language pre-training’’

Experience

Researcher (Huawei TopMinds), 2023.7 - Present, Huawei, Beijing, lead the Research & Development of Multimodal Training Framework on Ascend NPUs, Multimodal Data Construction, and MLLM’s Pretraining & Finetuning
Research Intern, 2022.12 - 2023.7, Huawei Cloud, Beijing. Mentor: Jianlong Chang, Qi Tian (IEEE Fellow)
Research Intern, 2021.5 - 2021.3, Microsoft AI, Beijing. Mentor: Can Xu
Research Intern (Tencent Rhino-Bird Elite Talent Program), 2019.4 - 2020.11, WeChat AI@Tencent, Beijing. Mentor: Fandong Meng

Selected Publications

Ziyi Ni, Minglun Han, Feilong Chen, Linghui Meng, Jing Shi, Pin Lv, Bo Xu, Vilas: Exploring the effects of vision and language context in automatic speech recognition, ICASPP 2024
Duzhen Zhang, Feilong Chen, Jianlong Chang, Xiuyi Chen, Qi Tian, Structure aware multi-graph network for multi-modal emotion recognition in conversations, TMM 2023
Duzhen Zhang, Feilong Chen, Xiuyi Chen, Dualgats: Dual graph attention networks for emotion recognition in conversations, ACL 2023
Duzhen Zhang, Yahan Yu, Feilong Chen, Xiuyi Chen, Decomposing logits distillation for incremental named entity recognition, SIGIR 2023
Feilong Chen, Minglun Han, Haozhi Zhao, Qingyang Zhang, Jing Shi, Shuang Xu, Bo Xu, X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages
Minglun Han, Feilong Chen, Jing Shi, Shuang Xu, Bo Xu, Knowledge transfer from pre-trained language models to cif-based speech recognizers via hierarchical distillation, Interspeech 2023
Feilong Chen, Minglun Han, Jing Shi, Shuang Xu, Bo XuEnhancing Visual Question Answering via Deconstructing Questions and Explicating Answers, Interspeech 2023
Feilong Chen, Duzhen Zhang, Xiuyi Chen, Jing Shi, Shuang Xu, Bo Xu, Unsupervised and pseudo-supervised vision-language alignment in visual dialog, ACM MM
Feilong Chen, Xiuyi Chen, Jiaxin Shi, Duzhen Zhang, Jianlong Chang, Qi Tian, HiVLP: Hierarchical vision-language pre-training for fast image-text retrieval
Xiuyi Chen, Feilong Chen, Shuang Xu, Bo Xu, A multi domain knowledge enhanced matching network for response selection in retrieval-based dialogue systems, ICASSP 2022
Feilong Chen, Xiuyi Chen, Shuang Xu, Bo Xu, Improving cross-modal understanding in visual dialog via contrastive learning, ICASPP 2022
Feilong Chen, Duzhen Zhang, Minglun Han, Xiuyi Chen, Jing Shi, Shuang Xu, Bo Xu, VLP: A survey on vision-language pre-training, Machine Intelligence Research
Feilong Chen, Xiuyi Chen, Can Xu, Daxin Jiang, Learning to ground visual objects for visual dialog, EMNLP 2021 Findings
Feilong Chen, Xiuyi Chen, Fandong Meng, Peng Li, Jie Zhou, GoG: Relation-aware graph-over-graph network for visual dialog, ACL 2021 Findings
Feilong Chen, Fandong Meng, Xiuyi Chen, Peng Li, Jie Zhou, Multimodal incremental transformer with visual grounding for visual dialogue generation, ACL 2021 Findings
Xiuyi Chen, Feilong Chen, Fandong Meng, Peng Li, Jie Zhou, Unsupervised knowledge selection for dialogue generation, ACL Findings
Xiuyi Chen, Fandong Meng, Peng Li, Feilong Chen, Shuang Xu, Bo Xu and Jie Zhou. Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation, EMNLP 2020
Feilong Chen, Fandong Meng, Jiaming Xu, Peng Li, Bo Xu and Jie Zhou. DMRM: A Dual-channel Multi-hop Reasoning Model for Visual Dialog, AAAI 2020

Selected Awards

2024, CBG President Team Award
2018, Outstanding Undergraduate Student of Anhui Province
2018, Tongze Scholarship awarded by Hefei University of Technology (Top 1%)
2018, Outstanding Undergraduate Student of Hefei University of Technology (Top 3)
2017, Second Prize in Chinese Undergraduate Computer Design Contest (Anhui Province)
2017, Second Prize in China College Students’ “Internet+” Innovation and Entrepreneurship Competition (Anhui Province)
2017, First Prize in Chinese Mathematical Contest in Modeling (Anhui Province)
2016, National Endeavor Fellowship awarded by the Ministry of Education, China (Top 1%)
2015, National Scholarship awarded by the Ministry of Education, China (Top 1%)