Fei Ma (马飞)

Fei Ma (马飞)

Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

Home

  Fei Ma is a Researcher, Principal Investigator, and Master’s Supervisor at Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), also known as Guangming Laboratory, where he leads the Media Intelligence team. He received his Ph.D. degree in Information and Communication Engineering from Tsinghua University and his B.S. degree in Communication Engineering from the University of Electronic Science and Technology of China (UESTC). His research lies at the intersection of generative artificial intelligence and affective computing. He has published over 40 papers in top journals such as TPAMI (IF: 18.6), Information Fusion (IF: 15.5), TAFFC (IF: 9.8), TMC (IF: 9.2), TIE (IF: 7.2), and CCF Tier-A conferences (NeurIPS, ICLR, ACL, AAAI, IJCAI, ACM MM). He has filed or been granted over 40 Chinese invention patents. He received the Outstanding Scientific Research Achievement Innovation Award at the China Hi-Tech Fair, and his self-developed AIGC short film “Chang’e Flying to the Moon” was featured on CCTV Video, CCTV.com, and CNR.com, gaining widespread attention.

  Before joining Guangming Laboratory, he worked at Huawei. This dual “academic + industrial” background drives his commitment to bridging the last mile between research and real-world deployment. His team focuses on human-centered multimodal content understanding and generation, as well as world models, including Multimodal LLMs, AIGC, Digital Human & Interaction, and Affective Computing.

📣 Recent News

[Jan. 2026] Three papers are accepted by ICLR.

[Jan. 2026] One paper is accepted by WWW.

[Dec. 2025] One patent is authorized.

[Nov. 2025] Our GMTalker project won the Outstanding Scientific Research Achievement Innovation Award at the 27th China Hi-Tech Fair.

[Nov. 2025] One paper is accepted by IEEE Transactions on Industrial Electronics; two papers are accepted by AAAI.

[Oct. 2025] GMTalker: A full-stack 3D interactive digital human solution officially released by Guangming Laboratory, with over 1000 GitHub stars!

[Sep. 2025] Two papers are accepted by NeurIPS.

[Jul. 2025] One paper is accepted by TPAMI.

[Jul. 2025] One paper is accepted by ECAI.

[Jul. 2025] Two papers are accepted by ACM MM. Congratulations to Yihong, one of my first PhD students!

[Jul. 2025] One paper is accepted by ICML 2025 R2-FM Workshop.

[Jun. 2025] Two papers are accepted by IROS. Congratulations to Yifan and Zixuan!

[May. 2025] One paper is accepted by IEEE Transactions on Affective Computing. Congratulations to Yifan and Yukan!

[May. 2025] One paper is accepted by ACL 2025. Congratulations to Congzhi!

[May. 2025] One paper is accepted by Information Fusion.

[Apr. 2025] Three papers are accepted by IJCAI 2025. Congratulations to Haiwei and Chenyang!

[Apr. 2025] One paper is accepted by ICMR 2025. Congratulations to Yifan!

[Apr. 2025] One paper is accepted by Information Fusion.

[Mar. 2025] Three papers are accepted by ICME 2025. Congratulations to Tao Feng, Xin Zhang, and Yang Xiang!

[Mar. 2025] One paper is accepted by IEEE TPAMI. Congratulations to Hongwei!

📝 Publications

  • * represents the first author, # represents the corresponding author.

  • For more paper information, please refer to the Google Scholar page.

Selected Journal Papers

1) F. Ma*, Y. Xie, Y. Li, Y. He, Y. Zhang, H. Ren, Z. Liu, W. Yao, F. Ren, F. Yu, S. Ni. A Review of Human Emotion Synthesis Based on Generative Technology. IEEE Transactions on Affective Computing, 2025. (IF: 9.6)

2) H. Hou, F. Ma*, Z. Li, F. Yu. VisualRWKV-HM: Enhancing Linear Visual-Language Models via Hybrid Mixing. Information Fusion, 2025. (IF: 14.8)

3) H. Ren, Y. Zhou, J. Zhu, X. Lin, H. Fu, Y. Huang, Y. Fang, F. Ma, H. Yu, B. Cheng. Rethinking Efficient and Effective point-based Networks for Event Camera Classification and Regression. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025. (IF: 20.8)

4) S. Chen, Z. Wu, K. Zhang, C. Li, B. Zhang, F. Ma, F. Yu, Q. Li. Exploring embodied multimodal large models: Development, datasets, and future directions. Information Fusion, 2025. (IF: 14.8)

5) F. Ma*, Y. Yuan, Y. Xie, H. Ren, I. Liu, Y. He, F. Ren, F. Yu, S. Ni. Generative Technology for Human Emotion Recognition: A Scoping Review. Information Fusion, 2024. (IF: 14.8)

6) C. Wang, H. Yu, X. Li, F. Ma, X. Wang, T. Taleb, V. Leung. Dependency-Aware Microservice Deployment for Edge Computing: A Deep Reinforcement Learning Approach with Network Representation. IEEE Transactions on Mobile Computing, 2024. (IF: 7.7)

7) Y. Liu, H. Hou, F. Ma #, S. Ni, F. Yu. MLLM-TA: Leveraging Multimodal Large Language Models for Precise Temporal Video Grounding. IEEE Signal Processing Letters, 2024. (IF: 3.2)

Selected Conference Papers

1) C. Zhang, J. Peng, Z. Wang, Y. Lai, H. Sun, H. Chang, F. Ma, W. Yu. VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism. ACL 2025. (CCF A)

2) H. Xue, Z. Zhang, M. Li, Z. Dai, F. Yu, F. Ma #, Z. Wu. VideoHumanMIB: Unlocking Appearance Decoupling for Video Human Motion In-betweening. IJCAI 2025. (CCF A)

3) W. Feng, Y. Zhu, R. Zhang, C. Wang, F. Ma, X. Wang, X. Li. Active Multimodal Distillation for Few-shot Action Recognition. IJCAI 2025. (CCF A)

4) G. Chen, Y. He, M. Yu, F. Yu, G. Xu, F. Ma, M. Li, G. Zhou. Inter3D: A Benchmark and Strong Baseline for Human-Interactive 3D Object Reconstruction. IJCAI 2025. (CCF A)

5) Y. Xie, F. Ma*, Y. Bin, Y. He, F. Yu. Audio-Driven Talking Face Video Generation with Joint Uncertainty Learning. ACM ICMR 2025.

6) Y. Xie, T. Feng, X. Zhang, X. Luo, Z. Guo, W. Yu, H. Chang, F. Ma #, F. Yu. PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis. AAAI 2025. (CCF A)

7) X. Xiang, Z. Dai, H. Xue, D. Wang, M. Li, Y. Yue, F. Ma #, W. Yu, H. Chang, F. Yu. ReMask-Animate: Refined Character Image Animation Using Mask-Guided Adapters. AAAI 2025. (CCF A)

8) L. Wang, S. Shi, F. Ma, F. Yu, P. Li, Y. He. Subgraph Invariant Learning towards Large-scale Graph Node Classification. AAAI 2025. (CCF A)

9) X. Luo, X. Zhang, Y. Xie, X. Tong, W. Yu, H. Chang, F. Ma #, F. Yu. CodeSwap: Symmetrically Face Swapping Based on Prior Codebook. ACM MM 2024. (CCF A)

10) L. Xiong, X. Cheng, J. Tan, X. Wu, X. Li, L. Zhu, F. Ma, M. Li, H. Xu, Z. Hu. SegTalker: Segmentation-based Talking Face Generation with Mask-guided Local Editing. ACM MM 2024. (CCF A)

Selected Chinese Patents

1) 马飞*，徐洪波，谢长岭，卓一瑶，罗奕明，李阳，纪奕泓。一种基于多模态大模型的跌倒检测方法、系统、终端及存储介质。202510512556.7

2) 马飞*，卓一瑶，施斯，董淳光。一种个性化数字人预问诊平台。202411030663.8

3) 马飞*，卓一瑶，侯皓文，尹东富，李海鹏。一种智能陪护方法、智能陪护系统及计算机存储介质。202411159025.6

4) 马飞*，徐洪波，卓一瑶，董淳光，施斯。一种基于多智能体的微短剧自动化生成方法、系统及终端。202411315872.7

5) 马飞*，彭亮，李明磊，怀宝兴。数字人视频的生成方法、装置、设备及存储介质。202310429308.7

6) 马飞*，彭亮，李明磊，怀宝兴。数字人多媒体资源的生成方法、装置、设备及存储介质。202310389438.2

7) 马飞*，李明磊，刘辉，杨昌鹏。一种评估方法、装置及设备。202310934271.3

8) 马飞*，陈志毅，李明磊，怀宝兴。一种虚拟形象的管理方法及相关系统。202310486823.9

9) 马飞*，李明磊，怀宝兴，戴宗宏。一种数字人绑定评估方法。202311218488.0

10) 李国健，马飞*，徐洪波，卓一瑶，谢长岭，朱海俊，赵豫鄂，胡赫。一种基于大模型的水利智慧语音交互方法、系统、终端及存储介质。202510512558.6

11) 张鑫，马飞*，卓一瑶，花霖。一种基于扩散模型生成语义掩码的多模态人脸编辑方法。202411056500.7

12) 谢奕凡，马飞*，卓一瑶，田甄。一种基于神经辐射场的语音驱动数字人视频生成方法。202411071122.X

13) 罗向阳，马飞*，徐洪波，卓一瑶，刘洲，董君心。一种具有一致性故事插画生成的框架。202411242121.7

14) 董君心，马飞*，贺颖，董淳光，施斯，侯皓文。网站网页主题风格切换方法、装置、计算机设备及存储介质。202411989061.5

15) 彭亮，马飞*，李明磊，怀宝兴。一种虚拟对象的动作图像数据生成方法、装置及相关设备。202310489294.8

🏆 Honors & Awards

  • 2025年 光明实验室优秀团队
  • 2025年 光明实验室优秀个人
  • 2025年 中国国际高新技术成果交易会优秀科研成果创新奖
  • 2024年 第十三届中国创新创业大赛创新挑战赛（宁波）解决方案优胜奖（赛道第一名）
  • 2024年 全国昇腾AI原生创新算子挑战赛（S2赛季）优秀奖（指导教师：马飞）
  • 2024年 深圳广告创意制作大赛AI创意生成类优秀奖

🏅 Membership

  • 中国中文信息学会情感计算专委会委员
  • 广东省图象图形学会情感计算专委会副秘书长
  • 广东省青年科学家协会会员
  • 数字深圳联合创新中心专家委员会委员
  • 深圳市光明社区科技委员

🎤 Invited Talks

  • [2025/12/28] “基于大模型与AIGC的情感智能：从感知理解到具身共情” —— AIGC 2025（第三届人工智能生成内容国际会议暨大模型应用创新大会），杭州
  • [2025/12/17] “生成式情感智能：从数字大脑到具身实体的跨越” —— 清华大学深圳国际研究生院，深圳
  • [2025/10/28] “基于多模态大模型的媒体内容理解与生成” —— 中山市青联大讲堂，电子科技大学中山学院，中山
  • [2025/10/17] “生成式情感智能：从多模态理解到具身交互” —— 安徽医科大学，合肥
  • [2024/10/20] “多模态情感计算” —— 2024年第十三届华人心理学家学术研讨会，中山大学深圳校区，深圳

🔍 Conference Reviewer / Area Chair

  • Conferences:

  NeurIPS（2025, 2023, 2022）

  ICML 2022

  ICLR（2025-2022）

  CVPR (2026-2025)

  AAAI 2026

  ACM MM (2025-2023)

  ICME (2023-2019)

  ICASSP 2023

  WACV 2026

  ICIP 2021

  ICONIP 2019

📚 Teaching

  • Data Thinking and Behavior, Fall 2025
  • Machine Learning, Spring 2025
  • Social Psychology and Behavioral Big Data, Spring 2023