📖 Educations

• 2013.09-2016.07, Ph.D. Dept. of Electronic Engineering, City University of Hong Kong.
• 2011.09-2013.06, M.E. Dept. of Electronic Engineering, Huazhong University of Science and Technology.
• 2007.09-2011.06, B.E. Dept. of Electronic Engineering, Huazhong University of Science and Technology.

💻 Work Experience

• 2026.05-present, Senior Staff Engineer, NextAI Research Institute, Chery Group.
• 2020.12-2026.05, Staff Engineer, Alipay, Ant Group.
• 2017.12-2020.12, Researcher, Deep Learning Group, MiniEye.
• 2016.07-2017.11, Researcher, Autonomous Driving Lab, Tencent.
• 2015.03-2015.08, Visiting Scholar, Brain Matrix Lab, Tsinghua University.

📄 Project Experience

• 2025.12-present, LLM/VLM/Agent Related. Domain-specific Training of LLMs and VLMs, Agentic AI etc.
• 2023.09-present, AIGC Related. Instruction Editing, Editing Evaluation, Audio-Driven Talking Human, Image/Video Generation, UI Generation etc.
• 2022.01-2023.09, Scene Digitization. Human ReID, Small Object Detection and Recognization, 3D Reconstruction and Retrival etc.
• 2020.12-present, Face Related. Liveness Detection, Emotion Detection, Face Detection etc.
• 2016.07-2020.11, Autonomous Driving. Traffic Scene Detection and Recognition etc.
• 2010.09-2016.07, Shearlet and Biological Signal Related. Image/Video Quality Assessment, Livness Detection, PPG Application etc.

📈 Highlighted Open Source Projects

AAAI 2026

EchoMimicV3: 1.3 B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation

Rang Meng, Yan Wang, Weipeng Wu, Ruobing Zheng, Yuming Li^✉, Chenguang Ma^✉

project code 

CVPR 2025

EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

Rang Meng, Xingyu Zhang, Yuming Li^✉, Chenguang Ma^✉

project code 

AAAI 2025

EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

Zhiyuan Chen^*, Jiajiong Cao^*, Zhiquan Chen, Yuming Li^✉, Chenguang Ma^✉

project code 

📝 Publications

† → Corresponding author

LLM/VLM/Agent

• Ma, X., Hu, Z., Wei, Y., Zhao, C., Chen, Y., Zhao, J., Li, Y.†, & Dai, C. “EviBack: Search-Agent Reinforcement Learning via Evidence-Constrained Teacher Backoff.” arXiv preprint arXiv:2607.23955 (2026). (code)

AIGC

• Meng, R., Wu, W., Yin, Y., Li, Y.†, & Ma, C. “EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation.” arXiv preprint arXiv:2602.13669 (2026).
• Meng, R., Wang, Y., Wu, W., Zheng, R., Li, Y.†, & Ma, C. “EchoMimicV3: 1.3 B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation.” Proceedings of the AAAI Conference on Artificial Intelligence. 2026. (code)
• Meng, R., Zhang, X., Li, Y.†, Ma, C. “EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2025. (code)
• Chen, Z., Cao, J., Chen, Z., Li, Y.†, Ma, C. “Echomimic: Lifelike audio-driven portrait animations through editable landmark conditions.” Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 39. No. 3. 2025. (code)
• Liu, T., Liu, Y., Li, B., Hu, W., Li, Y., & Ma, C. “Noise-Optimized Distribution Distillation for Dataset Condensation.” Proceedings of the 33rd ACM International Conference on Multimedia. 2025.
• Wang, Y., Teng, J., Cao, J., Li, Y., Ma, C., Xu, H., Luo, D. “Efficient Video Face Enhancement with Enhanced Spatial-Temporal Consistency.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2025. (code)
• Luo, W., Qin, H., Chen, Z., Wang, L., Zheng, D., Li, Y., … & Hu, W. “Visual-Instructed Degradation Diffusion for All-in-One Image Restoration.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2025.
• Lou, J., Luo, W., Liu, Y., Li, B., Ding, X., Hu, W., Li, Y., Ma, C. “Token Caching for Diffusion Transformer Acceleration.” arXiv preprint arXiv:2409.18523 (2024).

VLA/World Model/World Action Model

• Xu, Y., Yang, Y., Fan, Z., Liu, Y., Li, Y., Li, B., & Zhang, Z. “QVLA: Not All Channels Are Equal in Vision-Language-Action Model’s Quantization.” The Fourteenth International Conference on Learning Representations. 2026. (code)

Autonomous Driving

• Y. Li, J. Wang, T. Xing, T. Liu, C. Li, K. Su, "TAD16K: an enhanced benchmark for autonomous driving." IEEE International Conference on Image Processing (ICIP), September 2017. (code and datasets)

Face Liveness Detection

• L. Feng, L.M. Po, Y. Li, X. Xu, F. Yuan, C.H. Cheung, K.W. Cheung, "Integration of Image Quality and Motion Cues for Face Anti-Spoofing: a Neural Network Approach." Journal of Visual Communication and Image Representation, Volume 38, pp. 451-460, July 2016. (Youtube Demo)
• Y. Li, L. M. Po, X. Xu, L. Feng, F. Yuan, " Face Liveness Detection and Recognition using Shearlet based Feature Descriptiors." Proceeding of 2016 International Conference on Acoustics, Speech, and Signal Processing, ICASSP2016, Shanghai, China, pp. 874 - 877, March 2016.
• L. Feng, L.M. Po, Y. Li, F. Yuan, Face liveness detection using shearlet based feature descriptors." Journal of Electronic Imaging, 25(4), August 2016. (Youtube Demo)

Image/Video Quality Assessment

• L.M. Po, M. Liu, Y.F. Yuen, Y. Li, X. Xu, C. Zhou, P.H.W. Wong, K.W. Lau, H.T. Luk. "A Novel Patch Variance Biased Convolution Neural Network for No-Reference Image Quality Assessment." IEEE Trans. on Circuits and Systems for Video Technology (2019).
• M. Liu, L. M. Po, YAU Rehman, X. Xu, Y. Li, L. Feng, "Video copy detection by conducting fast searching of inverted files." Multimedia Tools and Applications (2018): 1-24.
• Y. Li, L. M. Po, L. Feng, F. Yuan, " No-reference Image Quality Assessment with Deep Convolutional Neural Networks." Proceeding of 2016 IEEE International Conference on Digital Signal Processing (DSP), Beijing, China, 16-18 October, 2016.
• Y. Li, L.M. Po, C.H. Cheung, X. Xu, L. Feng, F. Yuan, K.W. Cheung, "No-Reference Video Quality Assessment with 3D Shearlet Transform and Convolutional Neural Networks." IEEE Trans. on Circuits and Systems for Video Technology, Vol. 26, Issue 6, pp. 1044-1057, June 2015.
• Y. Li, L.M. Po, X. Xu, L. Feng, F. Yuan, C.H. Cheung, K.W. Cheung, "No-reference image quality assessment with shearlet transform and deep neural networks." Neurocomputing, Volume 154, Pages 94–109, April 2015.
• Y. Li, L.M. Po, X. Xu, L. Feng, "No-reference image quality assessment using statistical characterization in the shearlet domain." Signal Processing: Image Communication, Vol. 29, Issue 7, pp. 748-75, August 2014.
• M. Liu, L. M. Po, YAU Rehman, X. Xu, Y. Li, L. Feng, "A novel inverted index file based searching strategy for video copy detection." Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), 2017.
• F. Yuan, L. M. Po, L. Feng, Y. Li, X. Xu, "A Robust MEL-Bands Audio Fingerprint based on Spectral Local Maximum Energy for Content based Copy Detection." International Congress on Engineering and Information (ICEAI 2016), Osaka, Japan, May 2016.
• Y. Li, L. M. Po, X. Xu, L. Feng, F. Yuan, C. H. Cheung, K. W. Cheung, " No-Reference Image Quality Assessment Using Shearlet Transform and Stacked Autoencoders." Proceeding of 2015 IEEE International Symposium on Circuits and Systems, ISCAS2015, Lisbon, Portugal, May 2015.
• Y. Li, H. Cao, Z. Xu, ''No-reference image quality assessment using shearlet transform.'' Eighth International Symposium on Multispectral Image Processing and Pattern Recognition, October 2013.
• Y. Li, H. Cao, Z. Xu, ''An edge detection method for strong noisy image using shearlets.'' Seventh International Symposium on Multispectral Image Processing and Pattern Recognition, November 2011.

Biomedical Image/Video Processing

• L.M. Po, L. Feng, Y. Li, X. Xu, C.H. Cheung, K.W. Cheung, "Block-based adaptive ROI for remote photoplethysmography." Multimedia Tools and Applications 77.6 (2018): 6503-6529.
• L. Feng, L.M. Po, X. Xu, Y. Li, R. Ma, "Motion Resistant Remote Imaging Photoplethysmography Based on Optical Properties of Skin." IEEE Trans. on Circuits and Systems for Video Technology, Vol. 25, Issue 5, pp. 879-891, October 2014.
• L. M. Po, X. Xu, L. Feng, Y. Li, K. W. Cheung, C. H. Cheung, "Frame Adaptive ROI for Photoplethysmography Signal Extraction from Fingertip Video Captured by Smartphone." Proceeding of 2015 IEEE International Symposium on Circuits and Systems, ISCAS2015, Lisbon, Portugal, May 2015.
• L. Feng, L. M. Po, X. Xu, Y. Li, C. H. Cheung, K. W. Cheung, Y. Fang, "Dynamic ROI Based on K-Means for Remote Photoplethysmography." Proceeding of 2015 International Conference on Acoustics, Speech, and Signal Processing, ICASSP2015, April 2015.
• L. Feng, L. M. Po, X. Xu, Y. Li, " Motion artifacts suppression for remote imaging photoplethysmography ." 9th International Conference on Digital Signal Processing 2014, August 2014.

Others

• 张默, 李宇明, 史宗明 “基于人工智能深度学习的腹针穴位辅助定位系统的研发.” 中国针灸, Vol. 45, Issue 3, pp. 391-396, March 2025.

Patents

1. 张星宇, 李宇明, 马晨光, “对象检测方法、人脸识别方法及装置”, CN Patent, 121482839A, 2025.
2. 李宇明, 马晨光, 刘雨帆, 刘彤飞, “数据集蒸馏方法及装置”, CN Patent, 120807344A, 2025.
3. 李宇明, 马晨光, 刘雨帆, 罗文阳, 娄金铭, 李兵, 胡卫明, “一种事务数据处理方法、装置、存储介质及电子设备”, CN Patent, 120386591A , 2025.
4. 郭尚伟, 向涛, 李宇明, 马晨光, “后门检测方法和系统”, CN Patent, 120105411A, 2025.
5. 郭尚伟, 向涛, 李宇明, 马晨光, “基于分布式系统的模型训练方法、设备及系统”, CN Patent, 120107723A, 2025.
6. 李宇明, 马晨光, 刘雨帆, 娄金铭, 罗文阳, 李兵, 胡卫明, “图像生成方法、装置、设备与存储介质”, CN Patent, 119941551A, 2025.
7. 李宇明, 朱军, 丁菁汀, 李亮, “活体检测模型的训练方法、活体检测方法和系统”, CN Patent, 116468113A, 2023.
8. 李宇明, 丁菁汀, 李亮, “一种活体检测方法和系统”, CN Patent, 116453231A, 2023.
9. 李宇明, 丁菁汀, 李亮, “活体检测方法及系统”, CN Patent, 116189317A, 2023.
10. 李宇明, 丁菁汀, 李亮, “攻击对象检测方法及装置、介质、设备及产品”, CN Patent, 115482589A, 2022.
11. 李宇明, 丁菁汀, 李亮, “一种活体检测方法、装置、设备及介质”, CN Patent, 114821824A, 2022.
12. 李宇明, “活体检测方法、装置、设备及系统”, CN Patent, 114696988B, 2022. (granted)
13. 李宇明, 刘国清, 郑伟, 杨广, “车道线实例聚类方法、装置、电子设备和存储介质”, CN Patent, 112084988B, 2020. (granted)
14. 李宇明, 刘国清, 郑伟, 杨广, “基于特征空间的车道线处理方法、装置、车载终端和介质”, CN Patent, 112001378B, 2020. (granted)
15. 李宇明, 刘国清, 董颖, 郑伟, 杨广, “车辆盲区检测处理方法、装置、车载终端和存储介质”, CN Patent, 111923857B, 2020. (granted)
16. 李宇明, 刘国清, 郑伟, 杨广, “图像数据筛选方法、装置、计算机设备和存储介质”, CN Patent, 111274926B, 2020. (granted)
17. 李宇明, 刘国清, 郑伟, 杨广, 敖争光, “车头位置估计方法、装置、计算机设备和存储介质”, CN Patent, 111160370B, 2020. (granted)
18. 李宇明, 刘国清, 郑伟, 杨广, 敖争光, “泊车位检测方法、装置、计算机设备和存储介质”, CN Patent, 111160172B, 2020. (granted)
19. 李宇明, 刘国清, 郑伟, 杨广, 敖争光, “车道线检测方法、装置、计算机设备和存储介质”, CN Patent, 111178245B, 2020. (granted)
20. 李宇明, 刘国清, 郑伟, 杨广, 敖争光, “自动驾驶的视觉感知方法、装置、计算机设备和存储介质”, CN Patent, 111178253B, 2020. (granted)
21. L. M. Po, M. Liu, Y. F. Yuen, Y. Li, Xu, X. Xu, et al, “Patch selection for neural network based no-reference image quality assessment”, US Patent, 10789696B2, 2019. (granted)
22. 布礼文, 刘孟洋, 袁耀辉, 李宇明, 徐叙远等, “用于训练神经网络的图像块的选择方法及图像质量评价方法”, CN Patent, 110599439A, 2019.
23. 王珏, 王斌, 李宇明, 邢腾飞, 李成军, 苏奎峰, 陈仁, 向南, “交通信号灯状态识别方法、装置、车载控制终端及机动车”, CN Patent, 108804983B, 2018. (granted)
24. 邢腾飞, 李宇明, 王珏, 王斌, “一种交通灯识别方法及装置”, CN Patent, 108305475B, 2018. (granted)

🔍 Research Projects

• 2024, Core Member, “Acceleration and Optimization Techniques for Image Generation Algorithms in Large-Scale Models.” CAAI-AntGroup Fund.
• 2022, Core Member, “Core Cryptography-Driven Efficient Biometric Processing Technique.” CCF-AntGroup Fund.
• 2022, Core Member, “Trusted Identification and Privacy Protection Technologies for Personal Biometric Information in Internet Finance.” The “14th Five-Year Plan” National Key R&D Program Youth Scientist Project.
• 2019, Core Member, “Research and Application of High-Performance and High-Reliability Domain Controller System.” Guangdong Provincial Key Research and Development Project.
• 2018, Core Member, “Multisensor Fusion and Big Data-based Perception System for Autonomous Driving Vehicle.” Peacock Team Funding Fund of Shenzhen City.

💬 Invited Talks

• 2025.04, “EchoMimic: Generative Digital Human Technology and Applications.” QCon 2025 (全球软件开发大会). (PPT, Contents, Link)
• 2024.09, “Audio-driven AIGC Digital Human.” Inclusion 2024 (外滩大会). (Link)

🔅 Interests

• The Book of Changes (周易)☯️, Quantitative Trading💹, Throwing Cards (飞牌)♠️.
• I have been experiencing some confusion regarding certain hexagrams (䷈小畜,䷘无妄,䷝离). If you have a unique and insightful understanding of these hexagrams, I would be willing to pay for your consultation. Please feel free to contact me.