Yancheng Zhang
yczhang [at] ucf (dot) edu

I am a Ph.D. student at the Center for Research in Computer Vision, University of Central Florida, advised by Prof. Chen Chen. Prior to that, I received my Bachelor's degree in Computer Science from Sichuan University in 2023. During my time as an undergraduate, I was fortunate to work with Prof. Jiancheng Lv on computer vision at the Data Intelligence and Computing Art Laboratory.

My research interests focus on computer vision and privacy-preserving machine learning. If you find any research interests that we might share, please feel free to reach out.

Email  /  CV  /  Scholar  /  LinkedIn  /  Github

profile photo
News

Publication
blind-date E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models
Wenyan Cong, Yiqing Liang, Yancheng Zhang, Ziyi Yang, Yan Wang,
Boris Ivanovic, Marco Pavone, Chen Chen, Zhangyang Wang, Zhiwen Fan
Preprint, 2025

This work benchmarks 3D geometric foundation models (GFMs), offering in-depth evaluation of their spatial intelligence capabilities and insights for future research.

blind-date zkVC: Fast Zero-Knowledge Proof for Private and Verifiable Computing
Yancheng Zhang, Mengxin Zheng, Xun Chen, Jingtong Hu, Weidong Shi,
Lei Ju, Yan Solihin, Qian Lou
DAC, 2025

This work enhances the efficiency of Zero-Knowledge Proof (ZKP) protocols for matrix multiplication.

blind-date CipherPrune: Efficient and Scalable Private Transformer Inference
Yancheng Zhang, Jiaqi Xue, Mengxin Zheng, Mimi Xie, Mingzhe Zhang,
Lei Jiang, Qian Lou
ICLR, 2025

This work improves the efficiency of private Transformer inference in the secure two-party computation (2PC) setting.

blind-date DataSeal: Ensuring the Verifiability of Private Computation on Encrypted Data
Muhammad Husni Santriaji, Jiaqi Xue, Yancheng Zhang, Qian Lou, Yan Solihin
IEEE S&P, 2025

This work enhances the verifiability and integrity of private computation in FHE by incorporating algorithm-based fault tolerance.

blind-date HEBridge: Connecting arithmetic and logic operations in FV-style HE schemes
Yancheng Zhang, Xun Chen and Qian Lou
ACM CCS WAHC, 2024

This work enables the continuous evaluation of linear and non-linear operations within the BGV/BFV FHE schemes, enhancing their universality.

blind-date CryptoTrain: Fast Secure Training on Encrypted Dataset
Jiaqi Xue, Yancheng Zhang, Yanshan Wang, Xueqiang Wang, Hao Zheng, Qian Lou
ACM CCS LAMPS, 2024

This work accelerates FHE/MPC-based private training through correlation-aware polynomial convolution.

blind-date Encrypted Data Pruning for Confidential Training of Deep Neural Networks
Yancheng Zhang, Mengxin Zheng, Yuzhang Shang, Xun Chen, Qian Lou
NeurIPS, 2024

This work enhances FHE-based private training by incorporating and optimizing dynamic dataset pruning in the encrypted state.

blind-date CR-UTP: Certified Robustness against Universal Text Perturbations
Qian Lou, Xin Liang, Jiaqi Xue, Yancheng Zhang, Rui Xie, Mengxin Zheng
ACL, 2024

This work improves the certified robustness of language models against universal text perturbations through prompt search and ensemble methods.

blind-date Pure graph-guided multi-view subspace clustering
Hongjie Wu, Shudong Huang, Chenwei Tang, Yancheng Zhang, Jiancheng LV
Pattern Recognition, 2023

This work improves multi-view subspace clustering by leveraging the sparsity and connectivity of affinity graphs.

Services

Conference Reviewer: ICLR 2025.


Template from Jon Barron's website.