Tianfu Wu

Associate Professor@North Carolina State University·美国·OpenReview

研究方向

Deep learning · reinforcement learning · Statistical Modeling · learning and inference · Computer Vision · Pattern Recognition · image parsing · scene parsing

Tianfu Wu

HarmonyGNNs: Harmonizing Heterophily and Homophily in GNNs via Self-Supervised Node Encoding

Boosting Targeted Adversarial Transferability: A Generative Approach Guided by Core Target Samples

Continual Learning by Reuse, New, Adapt and Skip: A Hierarchical Exploration-Exploitation Approach

SimPlex-GT: A Simple Node-to-Cluster Graph Transformer for synergizing homophily and heterophily in Complex Graphs

Learning Universal Adversarial Perturbations for Ordered Top-K Targeted Attacks

GSBA$^K$: $top$-$K$ Geometric Score-based Black-box Attack

WeGeFT: Weight‑Generative Fine‑Tuning for Multi‑Faceted Efficient Adaptation of Large Models

Adversarial Perturbations Are Formed by Iteratively Learning Linear Combinations of the Right Singular Vectors of the Adversarial Jacobian

Revisiting and Expanding Targeted Universal Adversarial Perturbations

Generative Parameter Efficient Fine-Tuning

Continual Learning via Learning a Continual Memory in Vision Transformer

Differentiable Polygon Modeling for Object Instance Segmentation