Peng Xu Ph.D. student Department of Computer Science and Engineering The Chinese University of Hong Kong Email:pxu22@cse.cuhk.edu.hk

Biography

I am currently a Ph.D. student at the Department of Computer Science and Engineering, The Chinese University of Hong Kong (CUHK) , under the supervision of Prof. Bei Yu from Fall 2022. Previously, I received my B.S. in the Department of Software Engineering from Central South University, and my M.S. in the Department of Computer Science and Technology from Harbin Institute of Technology(Shenzhen).

Besides research, I love playing badminton in my spare time.

Research Interests

My research interests include:

• ML for Analog Physical Design: performance-driven analog placement, performance-driven analog routing, analog layout representaion learning.
• Automated Machine Learning: Neural Architecture Search, Graph Neural Networks, Parameter-Efficient Fine-Tuning.
• Optimization: bi-level & multi-level optimization, machine Learning in combinatonry optimization, sparse coding.

News

Education

• Ph.D. Computer Science and Engineering, The Chinese University of Hong Kong, Aug 2022 - present

• M.S. Computer Science and Technology, Harbin Institute of Technology, Sep 2019 - Jun 2021

• B.S. Software Engineering, Central South University, Sep 2015 - Jun 2019

Research & Professional Experience

• The Chinese University of Hong Kong, Shenzhen (CUHK-SZ), P.R. China, Jue. 2023 - present
  Visiting Student
  Topic: Performance-driven Analog Placement and Routing

• Tencent, Shenzhen, P.R. China, Nov. 2021 - Jan. 2022
  Research Intern, Interactive Entertainment Group
  Topic: Graph Neural Architecture Search for Social Networks

• SenseTime, Beijing, P.R. China, Jun. 2020 - Jun. 2021
  Research Intern, Exploration and Exploitation Group
  Topic: Neural Architecture Search with Big Single-Stage Models

• Intel Asia-Pacific R. & D. Center, Shanghai, P.R. China, Jul. 2018 - Jan. 2019
  Research Intern, Data Center Group
  Topic: Select Best Model Quantization Scheme with Reinforcement Learning

Publications

Conference Proceedings

• [C15] Hongduo Liu, Chen BAI, Peng Xu, Lihao Yin, Xianzhi Yu, Hui-Ling Zhen, Mingxuan Yuan, Tsung-Yi Ho, Bei Yu, “LLMShare: Optimizing LLM Inference Serving with Hardware Architecture Exploration”, in ACM/IEEE Design Automation Conference (DAC), San Francisco, Jun. 22–25, 2025.

• [C14] Ziyang Yu, Peng Xu, Zixiao WANG, Binwu Zhu, Qipan Wang, Yibo Lin, Runsheng Wang, Bei Yu, Martin Wong, “SDM-PEB: Spatial-Depthwise Mamba for Enhanced Post-Exposure Bake Simulation”, in ACM/IEEE Design Automation Conference (DAC), San Francisco, Jun. 22–25, 2025.

• [C13] Yuyang Ye, Xiangfei Hu, Yuchen Liu, Peng Xu, Yu Gong, Tinghuan Chen, Hao Yan, Bei Yu, Longxing Shi, “Rank-based Multi-objective Approximate Logic Synthesis via Monte Carlo Tree Search”, in ACM/IEEE Design Automation Conference (DAC), San Francisco, Jun. 22–25, 2025.

• [C12] Peng Xu, Su Zheng, Yuyang Ye, Chen Bai, Siyuan Xu, Hao Geng, Tsung-Yi Ho, Bei Yu, “RankTuner: When Design Tool Parameter Tuning Meets Preference Bayesian Optimization”, in IEEE/ACM International Conference on Computer-Aided Design (ICCAD), New Jersey, Oct. 27–31, 2024.

• [C11] Peng Xu, Guojin Chen, Keren Zhu, Tinghuan Chen, Tsung-Yi Ho, Bei Yu, “Performance-driven Analog Routing via Heterogeneous 3DGNN and Potential Relaxation”, in ACM/IEEE Design Automation Conference (DAC), San Francisco, Jun. 23–27, 2024.

• [C10] Hongduo Liu, Peng Xu, Yuan Pu, Lihao Yin, Hui-Ling Zhen, Mingxuan Yuan, Tsung-Yi Ho, Bei Yu, “NeuroSelect: Learning to Select Clauses in SAT Solvers”, in ACM/IEEE Design Automation Conference (DAC), San Francisco, Jun. 23–27, 2024.

• [C9] Guojin Chen, Hongquan He, Peng Xu, Hao Geng, Bei Yu, “Efficient Bilevel Source Mask Optimization”, in ACM/IEEE Design Automation Conference (DAC), San Francisco, Jun. 23–27, 2024.

• [C8] Xinyun Zhang*, Binwu Zhu*, Fangzhou Liu, Ziyi Wang, Peng Xu, Hong Xu, Bei Yu, “Disentangle, Align and Generalize: Learning A Timing Predictor from Different Technology Nodes”, in ACM/IEEE Design Automation Conference (DAC), San Francisco, Jun. 23–27, 2024.

• [C7] Haoyuan Wu*, Xinyun Zhang*, Peng Xu, Peiyu Liao, Xufeng Yao, Bei Yu, “p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models”, in AAAI Conference on Artificial Intelligence (AAAI), Vancouver, Feb. 20–27, 2024.

• [C6] Peng Xu, Jintao Li, Tsung-Yi Ho, Bei Yu, Keren Zhu, “Performance-Driven Analog Layout Automation: Current Status and Future Directions”, in IEEE/ACM Asian and South Pacific Design Automation Conference (ASPDAC), South Korea, Jan. 22–25, 2024. (Invited Paper)

• [C5] Su Zheng, Lancheng Zou, Peng XU, Siting Liu, Bei Yu, Martin Wong, “Lay-Net: Grafting Netlist Knowledge on Layout-Based Congestion Prediction”, in International Conference on Computer-Aided Design (ICCAD), San Francisco, Oct. 29–Nov. 02, 2023.

• [C4] Jiaqi Sun, Lin Zhang, Guangyi Chen, Peng Xu, Kun Zhang, Yujiu Yang, “Feature expansion for graph neural networks”, in International Conference on Machine Learning (ICML), Hawaii, Jul. 23–29, 2023.

• [C3] Peng Xu*, Lin Zhang*, Xuanzhou Liu, Jiaqi Sun, Yue Zhao, Haiqin Yang, Bei Yu, “Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks”, in International Conference on Machine Learning (ICML), Hawaii, Jul. 23–29, 2023.

• [C2] Peng Xu, Yihui Li, Yice Zhang, Jianxin Li Ruifeng Xu, GuozhongShi, and Feiran Hu, “Contrastive Learning for Multiple Models in One Supernet”, in International Conference on Cognitive Computing (ICCC), Virtual Event, Dec. 12-23, 2021.

• [C1] Auto quantization: Select best model quantization scheme with reinforcement learning, in Intel Design and Test Technology Conference (DTTC, 2019)

Journal Articles

• [J10] Peng Xu, Jindong Tu, Guojin Chen, Keren Zhu, Tinghuan Chen, Tsung-Yi Ho, Bei Yu, “PARoute2: Enhanced Analog Routing via Performance-Drive Guidance Generation”, accepted by IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD).

• [J9] Jindong Tu, Yapeng Li, Pengjia Li, Peng Xu, Qianru Zhang, Sanping Wan, Yongsheng Sun, Bei Yu, Tinghuan Chen, “SMART: Graph Learning-Boosted Subcircuit Matching for Large-scale Analog Circuits”, accepted by IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD).

• [J8] Lancheng Zou, Su Zheng, Peng Xu, Siting Liu, Bei Yu, Martin D.F. Wong, “Lay-Net: Grafting Netlist Knowledge on Layout-Based Congestion Prediction”, accepted by IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD).

• [J7] Xinyun Zhang, Binwu Zhu, Fangzhou Liu, Jiaxi Jiang, Ziyi Wang, Peng Xu, Hong Xu, Bei Yu, “Pre-Routing Timing Prediction Across Different Technology Nodes”, accepted by IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD).

• [J6] Yuyang Ye, Peng Xu, Lizheng Ren, Tinghuan Chen, Hao Yan, Bei Yu, Longxing Shi, “Learning-driven Physically-aware Large-scale Circuit Gate Sizing”, accepted by IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD)

• [J5] Peng Xu, Siyuan Xu, Tinghuan Chen, Guojin Chen, Tsung-Yi Ho, Bei Yu, “DeepOTF: Learning Equations-constrained Prediction for Electromagnetic Behavior”, accepted by ACM Transactions on Design Automation of Electronic Systems (TODAES).

• [J4] Peng Xu, Ke Wang, Mohammad Mehedi Hassan, Chien-Ming Chen, Weiguo Lin, Md. Rafiul Hassan, and Giancarlo Fortino, Adversarial Robustness in Graph-based Neural Architecture Search for Edge AI Transportation Systems, IEEE Transactions on Intelligent Transportation Systems (T-ITS), vol. 24, no. 8, pp. 8465-8474, Aug. 2023.

• [J3] Peng Xu, Ke Wang, Md. Rafiul Hassan, Mohammad Mehedi Hassan, and Chien-Ming Chen, An Interpretive Perspective: Adversarial Trojaning Attack on Neural-Architecture-Search Enabled Edge AI Systems, IEEE Transactions on Industrial Informatics (TII), vol. 19, no. 1, pp. 503-510, Jan. 2023.

• [J2] K. Wang, S. P. Xu, C. M. Chen, S. H. Islam, M. M. Hassan, C. Savaglio, P. Pace, and G. Aloi, "A Trusted Consensus Scheme for Collaborative Learning in the Edge AI Computing Domain", IEEE Network, vol. 35, no. 1, pp. 204-210, Jan 2021.

• [J1] E. K. Wang, S. P. Xu, C. Chen, and N. Kumar, "Neural-architecture-search-based Multiobjective Cognitive Automation System", IEEE Systems Journal, vol. 15, no. 2, pp. 2918-2925, June 2021.

Honours & Achievements

• Full Postgraduate Scholarship, The Chinese University of Hong Kong, 2020-2024
  

• Outstanding Graduate Awards, Harbin Institute of Technology, 2021
  

• First-class Scholarship, Harbin Institute of Technology for Master Students, 2019-2022
  

• Third Prize of CCF BDCI Competition Aliyun Database Sub-track, 4/684, 2019
  

• Outstanding Graduate Awards of Central South University, 2019
  

• First Prize of the Intel National Student Software Innovation Competition, 4/5000, 2018
  

• First-class scholarship of Central South University, 2015-2019
  

Professional Service

Journal Reviewer

• IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD)

• ACM Transactions on Design Automation of Electronic Systems (TODAES)

Conference Reviewer

• 2023 ACM/IEEE International Symposium on Physical Design (ISPD)