About me

Hi there! I am a Ph.D. at the Vision and Fusion Laboratory (IES) at Karlsruher Institut of Technologie (KIT), under the supervision of Prof. Jürgen Beyerer. Before that, I was a research scientist at the Institute for Visualization and Data Analysis (IVD) at KIT. I received my master’s degree in Control Science and Engineering and my bachelor’s degree in Automation from Nanjing University (NJU).

My research focuses on 3D computer vision and multimodal AI, spanning both applied and theoretical domains. On the 3D side, my work includes point cloud understanding, self-supervised learning, 3D shape generation, and language-guided 3D motion editing. I am also actively involved in the AgiProbot project (feel free to take the virtual tour !), where I work on point cloud segmentation, synthetic data generation, and sim2real transfer learning. On the multimodal side, I am interested in vision-language models, video-language understanding, and multimodal reasoning, with recent work on scalable long-form video narration and world models for situated reasoning. I have also worked on panoramic image understanding, open-vocabulary segmentation, and other vision-language tasks. Earlier in my research journey, I worked on 3D volumetric data synthesis and image style transfer. My master’s thesis was about quantum control.

📖 Selected Publications

• What if? Emulative simulation with world models for situated reasoning
• R. Liu, Y. Chen, Y. Zhang, J. Zheng, K. Peng, C. Wu, C. Huang, D. Wen, J. Zhang, K. Yang, R. Stiefelhagen
• ECCV 2026
• 📄 Paper | 💻 Code | 🎥 Video

• InterEdit: Navigating Text-Guided Multi-Human 3D Motion Editing
• Y. Yang, D. Wen, L. Qi,, W. Kong, J. Zheng, R. Liu, Y. Chen, C. Wu, K. Yang, Y. Fu, D. P. Paudel, L. Van Gool, and K. Peng
• ECCV 2026
• 📄 Paper | 💻 Code | 🎥 Video

• FlowNar: Scalable Streaming Narration for Long-Form Videos
• Z. Zhong, M. Martin, C. Wu, D. Schneider, F. Diederichs, J. Gall, J. Beyerer
• ICML 2026
• 📄 Paper | 💻 Code | 🏡 Homepage

• SAMBLE: Shape-Specific Point Cloud Sampling for an Optimal Trade-Off Between Local Detail and Global Uniformity
• C. Wu, Y. Wan, H. Fu, J. Pfrommer, Z. Zhong, J. Zheng, J. Zhang, and J. Beyerer
• CVPR 2025
• 📄 Paper | 💻 Code | 🏡 Homepage | 🎥 Video

• Open Panoramic Segmentation
• J. Zheng, R. Liu, Y. Chen, K. Peng, C. Wu, K. Yang, J. Zhang, R. Stiefelhagen
• ECCV 2024
• 📄 Paper | 💻 Code | 🏡 Homepage | 🎥 Video

• Attention-based Point Cloud Edge Sampling
• C. Wu, J. Zheng, J. Pfrommer, and J. Beyerer
• CVPR 2023 (Highlight Paper)
• 📄 Paper | 💻 Code | 🏡 Homepage | 🎥 Video

• Sim2real Transfer Learning for Point Cloud Segmentation: An Industrial Application Case on Autonomous Disassembly
• C. Wu, X. Bi, J. Pfrommer, A. Cebulla, S. Mangold, J. Beyerer
• WACV 2023
• 📄 Paper | 💻 Code | 🏡 Homepage | 🎥 Video

• SynMotor: A Benchmark Suite for Object Attribute Regression and Multi-task Learning
• C. Wu, L. Qiu, K. Zhou, J. Pfrommer, J. Beyerer
• VISAPP 2023 (Best Paper Finalist)
• 📄 Paper | 💻 Code | 🏡 Homepage | 🎥 Video

• Self-Supervised Generative-Contrastive Learning of Multi-Modal Euclidean Input for 3D Shape Latent Representations: A Dynamic Switching Approach
• C. Wu, J. Pfrommer, M. Zhou, J. Beyerer
• IEEE TMM
• 📄 Paper | 💻 Code