Chaolong Yang (杨超龙)

Home

Biography

I am a Ph.D. candidate in Computer Science at University of Liverpool and Xi'an Jiaotong-Liverpool University, supervised by Prof. Kaizhu Huang, Prof. Jie Sun and Prof. Guangliang Cheng. My research focuses on talking portrait synthesis, multimodal video generation, and 3D vision. Before starting my Ph.D., I worked as a Research Fellow at Duke Kunshan University and as an Assistant Machine Learning Engineer at Bright Dream Robotics.

News

• Jul. 2026 One conference demo paper was accepted in ACM Multimedia.
• Sep. 2025 One journal paper was accepted in International Journal of Computer Vision (IJCV).
• Jul. 2025 One conference demo paper was accepted in ACM Multimedia.
• Mar. 2025 One conference paper was accepted in ICME.
• Sep. 2024 One journal paper was accepted in Neural Networks (NN).
• Nov. 2023 One conference paper was accepted in ICONIP.
• Jul. 2023 One conference paper was accepted in ICCV.

Publications

Xemo-Talker: Unlock Emotions Explicitly for Audio-Driven Talking Portrait Synthesis

Chaolong Yang*, Yinuo Guo*, Kai Yao, Yuyao Yan, Jie Sun, Guangliang Cheng, Shibin Wu, Bin Dong, and Kaizhu Huang

arXiv preprint, 2026

Paper Code

KD-Avatar: A Real-Time Controllable Cross-Language Meeting Avatar System

Chaolong Yang*, Yinuo Guo*, Fei Cheng, Kai Yao, Yuyao Yan, Guangliang Cheng, Jie Sun, and Kaizhu Huang

ACM Multimedia Demo and Video Track (ACM MM), 2026 CCF-A

Video

Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait

Chaolong Yang*, Kai Yao*, Yuyao Yan, Chenru Jiang, Weiguang Zhao, Jie Sun, Guangliang Cheng, Yifei Zhang, Bin Dong and Kaizhu Huang

International Journal of Computer Vision (IJCV), 2025 CCF-A

Paper Code 300+ Stars

KDTalker++: Controllable Talking Portrait Generation with Audio, Text, and Expression Editing

Chaolong Yang*, Yinuo Guo*, Kai Yao, Yuyao Yan, Jie Sun, and Kaizhu Huang

ACM Multimedia Demo and Video Track (ACM MM), 2025 CCF-A

Paper Demo

From 2D images to 3D model: Weakly Supervised Multi-View Face Reconstruction with Deep Fusion

Weiguang Zhao*, Chaolong Yang*, Jianan Ye*, Yuyao Yan, Xi Yang, Bin Dong, Amir Hussain and Kaizhu Huang

International Conference on Multimedia and Expo (ICME), 2025 CCF-B

Paper Code

Open-Pose 3D zero-shot learning: Benchmark and challenges

Weiguang Zhao, Guanyu Yang, Rui Zhang, Chenru Jiang, Chaolong Yang, Yuyao Yan, Amir Hussain and Kaizhu Huang

Neural Networks (NN), 2024 CCF-B

Paper Code

Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation

Chaolong Yang, Yuyao Yan, Weiguang Zhao, Jianan Ye, Xi Yang, Amir Hussain, Bin Dong and Kaizhu Huang

International Conference on Neural Information Processing (ICONIP), 2023 CCF-C

Paper

Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization

Weiguang Zhao, Yuyao Yan, Chaolong Yang, Jianan Ye, Xi Yang and Kaizhu Huang

International Conference on Computer Vision (ICCV), 2023 CCF-A

Paper Code

Awards

• Sep. 2023 Doctoral Scholarship, University of Liverpool
• Mar. 2022 Degree awarded with Distinction, University of Liverpool
• Jun. 2019 Outstanding Graduates
• Dec. 2018 University Outstanding Student Huali Scholarship
• Nov. 2017 National Scholarship
• 2015-2019 Outstanding Student Scholarship First Prize twice, Second Prize once

Patents

• Jul. 2025 CN202310621403.7, A method for generating defect samples
• Feb. 2025 CN202311360007.X, 3D point cloud zero-shot classification method
• Aug. 2024 CN202111579569.4, 3D face model reconstruction method
• Jul. 2023 CN201911372226.3, Copywriting generation method
• Feb. 2023 CN202010002108.X, Drawing image positioning and proofreading method
• Nov. 2020 CN201911070968.0, A method and system for adjusting a graphic design framework
• Jul. 2020 CN201911289942.5, Image processing method and device
• Jun. 2020 CN201911315035.3, Sunshine duration analysis method

Experience

• 2023 - now Ph.D., Computer Science, University of Liverpool
• 2022 - 2023 Research Fellow, Duke Kunshan University
• 2020 - 2022 MRes, Pattern Recognition and Intelligent Systems, University of Liverpool
• 2019 - 2020 Assistant Machine Learning Engineer, Bright Dream Robotics
• 2015 - 2019 B.Eng., Automation, Guangdong University of Technology Huali College

Service

• Conference Reviewer: CVPR 25/26, ECCV 26
• Journal Reviewer: Pattern Recognition, TCSVT, Cognitive Computation, Neural Networks

Biography

I am a Ph.D. candidate in Computer Science at University of Liverpool and Xi'an Jiaotong-Liverpool University, supervised by Prof. Kaizhu Huang, Prof. Jie Sun and Prof. Guangliang Cheng. My research focuses on talking portrait synthesis, multimodal video generation, and 3D vision. Before starting my Ph.D., I worked as a Research Fellow at Duke Kunshan University and as an Assistant Machine Learning Engineer at Bright Dream Robotics.

News

• Jul. 2026 One conference demo paper was accepted in ACM Multimedia.
• Sep. 2025 One journal paper was accepted in International Journal of Computer Vision (IJCV).
• Jul. 2025 One conference demo paper was accepted in ACM Multimedia.
• Mar. 2025 One conference paper was accepted in ICME.
• Sep. 2024 One journal paper was accepted in Neural Networks (NN).
• Nov. 2023 One conference paper was accepted in ICONIP.
• Jul. 2023 One conference paper was accepted in ICCV.

Publications

Xemo-Talker: Unlock Emotions Explicitly for Audio-Driven Talking Portrait Synthesis

Chaolong Yang*, Yinuo Guo*, Kai Yao, Yuyao Yan, Jie Sun, Guangliang Cheng, Shibin Wu, Bin Dong, and Kaizhu Huang

arXiv preprint, 2026

Paper Code

KD-Avatar: A Real-Time Controllable Cross-Language Meeting Avatar System

Chaolong Yang*, Yinuo Guo*, Fei Cheng, Kai Yao, Yuyao Yan, Guangliang Cheng, Jie Sun, and Kaizhu Huang

ACM Multimedia Demo and Video Track (ACM MM), 2026 CCF-A

Video

Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait

Chaolong Yang*, Kai Yao*, Yuyao Yan, Chenru Jiang, Weiguang Zhao, Jie Sun, Guangliang Cheng, Yifei Zhang, Bin Dong and Kaizhu Huang

International Journal of Computer Vision (IJCV), 2025 CCF-A

Paper Code 300+ Stars

KDTalker++: Controllable Talking Portrait Generation with Audio, Text, and Expression Editing

Chaolong Yang*, Yinuo Guo*, Kai Yao, Yuyao Yan, Jie Sun, and Kaizhu Huang

ACM Multimedia Demo and Video Track (ACM MM), 2025 CCF-A

Paper Demo

From 2D images to 3D model: Weakly Supervised Multi-View Face Reconstruction with Deep Fusion

Weiguang Zhao*, Chaolong Yang*, Jianan Ye*, Yuyao Yan, Xi Yang, Bin Dong, Amir Hussain and Kaizhu Huang

International Conference on Multimedia and Expo (ICME), 2025 CCF-B

Paper Code

Open-Pose 3D zero-shot learning: Benchmark and challenges

Weiguang Zhao, Guanyu Yang, Rui Zhang, Chenru Jiang, Chaolong Yang, Yuyao Yan, Amir Hussain and Kaizhu Huang

Neural Networks (NN), 2024 CCF-B

Paper Code

Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation

Chaolong Yang, Yuyao Yan, Weiguang Zhao, Jianan Ye, Xi Yang, Amir Hussain, Bin Dong and Kaizhu Huang

International Conference on Neural Information Processing (ICONIP), 2023 CCF-C

Paper

Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization

Weiguang Zhao, Yuyao Yan, Chaolong Yang, Jianan Ye, Xi Yang and Kaizhu Huang

International Conference on Computer Vision (ICCV), 2023 CCF-A

Paper Code

Awards

• Sep. 2023 Doctoral Scholarship, University of Liverpool
• Mar. 2022 Degree awarded with Distinction, University of Liverpool
• Jun. 2019 Outstanding Graduates
• Dec. 2018 University Outstanding Student Huali Scholarship
• Nov. 2017 National Scholarship
• 2015-2019 Outstanding Student Scholarship First Prize twice, Second Prize once

Patents

• Jul. 2025 CN202310621403.7, A method for generating defect samples
• Feb. 2025 CN202311360007.X, 3D point cloud zero-shot classification method
• Aug. 2024 CN202111579569.4, 3D face model reconstruction method
• Jul. 2023 CN201911372226.3, Copywriting generation method
• Feb. 2023 CN202010002108.X, Drawing image positioning and proofreading method
• Nov. 2020 CN201911070968.0, A method and system for adjusting a graphic design framework
• Jul. 2020 CN201911289942.5, Image processing method and device
• Jun. 2020 CN201911315035.3, Sunshine duration analysis method

Career

Experience

• 2023 - now Ph.D., Computer Science, University of Liverpool
• 2022 - 2023 Research Fellow, Duke Kunshan University
• 2020 - 2022 MRes, Pattern Recognition and Intelligent Systems, University of Liverpool
• 2019 - 2020 Assistant Machine Learning Engineer, Bright Dream Robotics
• 2015 - 2019 B.Eng., Automation, Guangdong University of Technology Huali College

Service

• Conference Reviewer: CVPR 25/26, ECCV 26
• Journal Reviewer: Pattern Recognition, TCSVT, Cognitive Computation, Neural Networks