Sketch2NeRF: Multi-view Sketch-guided Text-to-3D Generation

no code implementations • 25 Jan 2024 • Minglin Chen, Weihao Yuan, Yukun Wang, Zhe Sheng, Yisheng He, Zilong Dong, Liefeng Bo, Yulan Guo

We propose a novel synchronized generation and reconstruction method to effectively optimize the NeRF.

3D Generation Text to 3D

EFMVFL: An Efficient and Flexible Multi-party Vertical Federated Learning without a Third Party

no code implementations • 17 Jan 2022 • Yimin Huang, Xinyu Feng, Wanwan Wang, Hao He, Yukun Wang, Ming Yao

In most VFL frameworks, to protect the security and privacy of the participants' local data, a third party is needed to generate homomorphic encryption key pairs and perform decryption operations.

regression Vertical Federated Learning

Certified Distributional Robustness via Smoothed Classifiers

no code implementations • 1 Jan 2021 • Jungang Yang, Liyao Xiang, Ruidong Chen, Yukun Wang, Wei Wang, Xinbing Wang

We focus on certified robustness of smoothed classifiers in this work, and propose to use the worst-case population loss over noisy inputs as a robustness metric.

Certified Distributional Robustness on Smoothed Classifiers

no code implementations • 21 Oct 2020 • Jungang Yang, Liyao Xiang, Ruidong Chen, Yukun Wang, Wei Wang, Xinbing Wang

For smoothed classifiers, we propose the worst-case adversarial loss over input distributions as a robustness certificate.