Dingcheng Yang   Algorithm Engineer Room 2308, Bio-Island International Apartments WeRide Guangzhou, China, 510320. Email: dingcheng.yang@realai.ai Github: ydc123 [Curriculum Vitae] [Google Scholar]

Biography

I received my Ph.D. from Tsinghua University in 2024, where I was fortunate to be advised by Prof. Wenjian Yu. During my Ph.D., I conducted research on adversarial attack/defense, AI4EDA, and deep neural network compression. Prior to this, I obtained my bachelor's degree from Tsinghua University in June 2019. I was an intern in the RealAI from November 2018 to December 2024.

Now, I am an algorithm engineer at WeRide, focus on autonomous driving technologies.

Competitions

• Our team (Dingcheng Yang, Xiao Yang, Shilong Liu, Zihao Xiao, Yinpeng Dong) won the first place in the GeekPwn DeepFake competition (October 24th, 2020).
• Our team (Dingcheng Yang, Lingjie Li) won the first place in the EDAthon Contest (August 7th, 2020).
• Our team (Dingcheng Yang, Shuyu Cheng, Xiao Yang, Yinpeng Dong) won the first place in the GeekPwn CAAD CTF competitions (October 24th, 2019).

Publications

• On the multi-modal vulnerability of diffusion models
  Dingcheng Yang^*, Yang Bai^*, Xiaojun Jia, Yang Liu, Xiaochun Cao, and Wenjian Yu (^* Equal contribution)
  International Conference on Machine Learning (ICML) Workshop, Vienna, Austria, Jul. 2024
  [paper] [code]
• Training better CNN models for 3-D capacitance extraction with neural architecture search
  Haoyuan Li^*, Dingcheng Yang^* and Wenjian Yu (^* Equal contribution)
  Design, Automation & Test in Europe Conference (DATE), Valencia, Spain, 2024.
  
• Boosting the adversarial transferability of surrogate models with dark knowledge
  Dingcheng Yang, Zihao Xiao, Wenjian Yu
  International Conference on Tools with Artificial Intelligence (ICTAI), Atlanta, USA, 2023.
  [paper] [code]
• Generating adversarial examples with better transferability via masking unimportant parameters of surrogate model
  Dingcheng Yang, Wenjian Yu, Zihao Xiao, Jiaqi Luo
  International Joint Conference on Neural Networks (IJCNN), Queensland, Australia, 2023.
  [paper] [code]
• CNN-Cap: Effective Convolutional Neural Network Based Capacitance Models for Interconnect Capacitance Extraction
  Dingcheng Yang, Haoyuan Li, Wenjian Yu, Yuanbo Guo, Wenjie Liang
  ACM Transactions on Design Automation of Electronic Systems (TODAES), 2023.
  [paper] [code]
• RobFR: Benchmarking Adversarial Robustness on Face Recognition
  Xiao Yang, Dingcheng Yang, Yinpeng Dong, Wenjian Yu, Hang Su, Jun Zhu
  [arxiv] [code]
• DP-Nets: Dynamic Programming Assisted Quantization Schemes for DNN Compression and Acceleration
  Dingcheng Yang, Wenjian Yu, Xiangyun Ding, Ao Zhou, Xiaoyi Wang
  Integration, the VLSI Journal, 2021.
  [paper]
• CNN-Cap: Effective Convolutional Neural Network Based Capacitance Models for Full-Chip Parasitic Extraction
  Dingcheng Yang, Wenjian Yu, Yuanbo Guo, Wenjie Liang
  International Conference on Computer-Aided Design (ICCAD), Munich, Germany, 2021
  [paper] [code]
• Dynamic Programming Assisted Quantization Approaches for Compressing Normal and Robust DNN Model
  Dingcheng Yang, Wenjian Yu, Haoyuan Mu, Gary Yao
  Asia and South Pacific Design Automation Conference (ASPDAC), Tokyo, Japan, 2021
  [paper]
• Optimal Algorithm for Profiling Dynamic
  Dingcheng Yang, Wenjian Yu, Junhui Deng, Shenghua Liu
  International Conference on Extending Database Technology (EDBT), Lisbon, Portugal, 2019.
  [paper]
• Pose2Seg: Detection Free Human Instance Segmentation
  Songhai Zhang, Ruilong Li, Xin Dong, Paul L. Rosin, Zixi Cai, Xi Han, Dingcheng Yang, Haozhi Huang, Shimin Hu
  IEEE conference on computer vision and pattern recognition (CVPR), Long Beach, USA, 2019.
  [paper] [code]