Weili Nie
Papers
1
Total Citations
10
H-Index
1
About
Weili Nie is a leading researcher at the intersection of generative AI, 3D computer vision, and adversarial machine learning. His work focuses on fortifying deep learning systems against security threats, particularly in safety-critical domains like autonomous driving and robotics. Nie is best known for pioneering diffusion-driven purification methods for 3D point cloud recognition, notably through his highly cited paper "PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition" (2022, 10+ citations). This work introduced a novel defense mechanism that leverages diffusion models to cleanse adversarial perturbations from 3D point cloud data, addressing a fundamental vulnerability in deep learning-based perception systems. Beyond this, Nie has made significant contributions to generative modeling, including diffusion models for image synthesis and controllable generation. His research has been recognized for bridging the gap between theoretical robustness and practical deployment, earning him invitations to top-tier conferences and collaborations with industry leaders. With a growing citation impact, Nie continues to shape the future of trustworthy AI in 3D perception and generative modeling.
Research Focus
Key Achievements
Top Papers
- 1