Tianfu Wu

Biography

Tianfu Wu is an associate professor in the Department of Electrical and Computer Engineering at NC State University. He is currently the PI of the laboratory of interpretable Visual Modeling, Computing and Learning (iVMCL).  He received his Ph.D. in statistics from UCLA under the supervision by Prof. Song-Chun Zhu. His research focuses on interpretable Visual Modeling, Computing and Learning, often motivated by the tasks of pursuing a unified framework for AI to ALTER (Ask, Learn, Test, Explain and Refine) in a trustworthy, robust and responsive way for AIGCGT (AI Generated Content and Ground-Truth).

Education

• Ph.D. 2011
  Statistics
  University of California, Los Angeles

Recent Publications

• Adversarial Perturbations Are Formed by Iteratively Learning Linear Combinations of the Right Singular Vectors of the Adversarial Jacobian (2025)
• DiffMesh: A Motion-aware Diffusion Framework for Human Mesh Recovery from Videos (2025)
• GSBA$\textasciicircumK$: $top$-$K$ Geometric Score-based Black-box Attack (2025)
• H$^3$GNNs: Harmonizing Heterophily and Homophily in GNNs via Joint Structural Node Encoding and Self-Supervised Learning (2025)
• ScaleLSD: Scalable Deep Line Segment Detection Streamlined (2025)
• WeGeFT: Weight‑Generative Fine‑Tuning for Multi‑Faceted Efficient Adaptation of Large Models (2025)
• A Pixel Is Worth More Than One 3D Gaussians in Single-View 3D Reconstruction (2024)
• Enhancing Approximate Message Passing via Diffusion Models Towards On-Device Intelligence (2024)
• High-Speed Receiver Transient Modeling with Generative Adversarial Networks (2024)
• Multi-View Attentive Contextualization for Multi-View 3D Object Detection (2024)