---

Brief Biography

Ping Guo is the Chief AI Scientist at Hong Kong Yuwin Technology Co., Ltd. He obtained his Ph.D. degree from City University of Hong Kong, supervised by Prof. Qingfu Zhang (Chair Professor, IEEE Fellow).

His research vision is to develop self-improving AI systems towards artificial general intelligence. To this end, he leverages evolutionary computation, large language models, and computational intelligence methods to solve complex optimization problems in real-world applications. His current research interests include:

• Evolutionary Computation & Optimization — multi-objective & many-objective optimization, hypervolume subset selection, evolutionary algorithm design, computational intelligence applications
• LLM-Driven Algorithm Design — automated heuristic & algorithm design, agentic meta-optimization, symbolic regression & program synthesis
• AI for Code & Hardware — automated code optimization, CUDA kernel evolution, Verilog / RTL generation, AI for EDA
• Trustworthy & Adversarial ML — adversarial machine learning, model robustness, multi-objective adversarial attacks
• AI + X — personalized federated learning, edge LLM inference & embodied intelligence

Throughout his academic journey, he has had the privilege of collaborating with distinguished researchers: Prof. Qingchuan Zhao, Dr. Xi Lin, and Dr. Cheng Gong.

---

Selected Publications

See the full publication list. (Bold = Ping Guo; † = equal contribution.)

1. CVPR'2026 Few-for-Many Personalized Federated Learning
   Ping Guo, Tiantian Zhang, Xi Lin, Xiang Li, Zhi-Ri Tang, Qingfu Zhang
2. AAAI'2026 CoEvo: Continual Evolution of Symbolic Solutions Using Large Language Models
   Ping Guo, Qingfu Zhang, Xi Lin arXiv Code
3. NeurIPS'2025 SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning
   Yiting Wang†, Wanghao Ye†, Ping Guo†, Yexiao He†, et al., Ang Li arXiv Code
4. CVPR'2025 MOS-Attack: A Scalable Multi-Objective Adversarial Attack Framework
   Ping Guo, Cheng Gong, Xi Lin, Fei Liu, Zhichao Lu, Qingfu Zhang, Zhenkun Wang PDF Code DOI
5. IEEE TBD EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models
   Ping Guo, Chenyu Zhu, Siyuan Chen, Fei Liu, Xi Lin, Zhichao Lu, Kuien Liu, Chaoning Zhang, Qingfu Zhang arXiv
6. IEEE TBD EvoVerilog: Large Language Model Assisted Evolution of Verilog Code
   Ping Guo†, Yiting Wang†, Wanghao Ye, Yexiao He, Ziyao Wang, Xiaopeng Dai, Ang Li, Qingfu Zhang arXiv
7. IEEE TETCI Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume
   Ping Guo, Cheng Gong, Xi Lin, Zhiyuan Yang, Qingfu Zhang PDF DOI
8. IEEE TBD PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks
   Ping Guo, Xiang Li, Xi Lin, Zhongying Chen, Qingchuan Zhao, Sheng Zheng, Chaoning Zhang, Qingfu Zhang arXiv
9. arXiv Quality-Diversity Optimization as Multi-Objective Optimization
   Xi Lin†, Ping Guo†, Yilu Liu, Qingfu Zhang, Jianyong Sun arXiv

---

News

• 02/2026Our paper "Few-for-Many Personalized Federated Learning" has been accepted by CVPR 2026 (CCF A)!
• 11/2025Our paper "CoEvo: Continual Evolution of Symbolic Solutions Using Large Language Models" has been accepted by AAAI 2026 (CCF A)! [arXiv]
• 09/2025Our paper "SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning" has been accepted by NeurIPS 2025 (CCF A)! [arXiv]
• 03/2025Our paper "MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework" has been accepted by CVPR 2025! [Paper] [CVPR]
• 11/2024Our paper "Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume" has been accepted by IEEE TETCI! [Paper] [IEEE]