معرفی
Tianfu Wu is an Associate Professor in the Department of Electrical and Computer Engineering at NC State University. He serves as the Principal Investigator (PI) for the laboratory of interpretable Visual Modeling, Computing and Learning (iVMCL). His research focuses on developing trustworthy and robust AI frameworks for Visual Modeling, Computing, and Learning, particularly through the concept of ALTER (Ask, Learn, Test, Explain, Refine) and AIGCGT (AI Generated Content and Ground-Truth).
Education:
- Ph.D. in Statistics (2011), University of California, Los Angeles (UCLA), supervised by Professor Song-Chun Zhu
Research Interests:
Tianfu Wu's work bridges interpretable AI, machine learning, and computer vision. His research emphasizes unifying AI frameworks for tasks like 3D reconstruction, neural networks, and geometric modeling, with a focus on robustness, responsiveness, and trustworthiness.
Publications Overview:
Recent publications highlight advancements in diffusion models, 3D object detection, and adversarial attacks. Key topics include human mesh recovery from videos, multi-view contextualization, wireframe parsing, and Byzantine-resilient gradient descent algorithms. These works intersect computer vision, deep learning, and AI security, often targeting applications in autonomous systems and efficient on-device intelligence.
Labs and Teams:
He leads the iVMCL lab, dedicated to interpretable visual modeling and learning, fostering interdisciplinary research in AI and computer vision.
