👋 About me

I am Zibo Wang(王梓博), a fifth-year Ph.D. student at NASA Group, State Key Laboratory for Novel Software Technology, Nanjing University.
I am currently under the supervision of Prof. Chen Tian and Dr. Zhibin Wang. I am expected to graduate in June 2027.

This is my Chinese CV. My research interests lie in the areas of:

Energy efficiency and memory optimization during training
Optimization and acceleration during inference

📖 Educations

2022.09 - (now), Nanjing University, China. Ph.D.
2018.09 - 2022.06, Nanjing University, China. Bachelor.

🔥 News

2026.08: 🎉🎉 Paper: NetMoE is conditionally accepted by EuroSys 2027.
2026.04: 🎉🎉 Paper: STAR is accepted by HPDC 2026.
2026.03: 🎉🎉 Paper: SmartSwap is accepted by DAC 2026.
2025.11: 🎉🎉 Awarded Guodian Nanjing Automation Scholarship (国电南自奖学金).
2025.04: 🎉🎉 Paper: Hermes is accepted by ATC 2025.
2025.01: 🎉🎉 Paper: Yuhang’s paper is accepted by ASPLOS 2025.
2024.10: 🎉🎉 Paper: DVFS paper is accepted by ASPLOS 2025.
2023.06: 🎉🎉 Paper: AFNFA is accepted by APNet 2023.

📝 Publications

电信科学星脉3.0：面向MoE模型训推一体的大规模高性能网络设计与实践
- 👤 王亚晨, 夏寅贲, 王梓博, 曹培睿, 王智彬

EuroSys’27 NetMoE: Orchestrating Fine-Grained Overlap for Efficient Distributed MoE Inference.
- 👤 Zibo Wang, Yadong Liu, Zhehao Lin, Peisheng Guo, Zhirui Zhu, Zuxi Chen, Qianyu Jiang, Tiancheng Weng, Xingyi Li, Xinxin Liu, Xiaojie Huang, Yinben Xia, Yuxi Wang, Mingzhuo Chen, Xuan Zhang, Weizhen Dang, Hao Lu, Yuanyuan Gong, Xiang Li, ZeKun He, Yachen Wang, Xianneng Zou, Yiran Zhang, Rong Gu, Qingkai Meng, Peirui Cao, Zhaochen Zhang, Qing Wang, Zhibin Wang, Sheng Zhong, Chen Tian

HPDC’26 STAR: Decode-Phase Rescheduling for LLM Inference. 📄 Paper
- 👤 Zhibin Wang, Zetao Hong, Xue Li, Zibo Wang, Shipeng Li, Qingkai Meng, Qing Wang, Chengying Huan, Rong Gu, Sheng Zhong,
  Chen Tian.

DAC’26 SmartSwap: Swap-Based Memory Optimization for LLM Training under Varying Operator Sequences. 📄 Paper
- 👤 Zibo Wang, Yuhang Zhou, Zhibin Wang, Shipeng Li, Xinjing Huang, Chendong Cai, Bingxu Mu, Yuqing Sun, Zhiheng Hu, Bin She,
  Shu You, Guanghuan Fang, Rong Gu, Wanchun Dou, Guihai Chen, Chen Tian

ATC’25 Accelerating Model Training on Ascend Chips: An Industrial System for Profiling, Analysis and Optimization. 📄 Paper 📊 Slides
- 👤 Yuhang Zhou, Zibo Wang, Zhibin Wang, Ruyi Zhang, Chen Tian, Xiaoliang Wang, Wanchun Dou, Guihai Chen, Binqiang Wang,
  Yonghong Tian, Yan Zhang, Hui Wang, Fuchun Wei, Boquan Sun, Jingyi Zhang, Bin She, Teng Su, Yifan Yao, Chunsheng Li,
  Ziyang Zhang, Yaoyuan Wang, Bin Zhou, Guyue Liu

ASPLOS’25 Squeezing Operator Performance Potential for the Ascend Architecture. 📄 Paper
- 👤 Yuhang Zhou, Zhibin Wang, Guyue Liu, Shipeng Li, Xi Lin, Zibo Wang, Yongzhong Wang, Fuchun Wei, Jingyi Zhang, Zhiheng Hu,
  Yanlin Liu, Chunsheng Li, Ziyang Zhang, Yaoyuan Wang, Bin Zhou, Wanchun Dou, Guihai Chen, Chen Tian

ASPLOS’25 Using Analytical Performance/Power Model and Fine-Grained DVFS to Enhance AI Accelerator Energy Efficiency. 📄 Paper
📊 Slides
- 👤 Zibo Wang, Yijia Zhang, Fuchun Wei, Bingqiang Wang, Yanlin Liu, Zhiheng Hu, Jingyi Zhang, Xiaoxin Xu, Jian He,
  Xiaoliang Wang, Wanchun Dou, Guihai Chen, Chen Tian

APNet’23 AFNFA: An Approach to Automate NCCL Configuration Exploration. 📄 Paper
- 👤 Zibo Wang, Yuhang Zhou, Chen Tian, Xiaoliang Wang, Xianping Chen

📰 Preprints

Arxiv 25 Accelerating Mixture-of-Experts Inference by Hiding Offloading Latency with Speculative Decoding. 📄 Paper
- 👤 Zhibin Wang, Zhonghui Zhang, Yuhang Zhou, Zibo Wang, Mo Zhou, Peng Jiang, Weilin Cai, Chengying Huan, Rong Gu, Sheng Zhong, Chen Tian

Arxiv 25 Echo: Efficient Co-Scheduling of Hybrid Online-Offline Tasks for Large Language Model Serving. 📄 Paper
- 👤 Zhibin Wang, Shipeng Li, Xue Li, Yuhang Zhou, Zhonghui Zhang, Zibo Wang, Rong Gu, Chen Tian, Kun Yang, Sheng Zhong

🎖 Honors and Awards

2025.12: Awarded Outstanding Graduate Model of Nanjing University (南京大学优秀研究生标兵).
2025.11: Guodian Nanjing Automation Scholarship (国电南自奖学金)
2025.04: Postgraduate Research & Practice Innovation Program of Jiangsu Province (江苏省研究生科研与实践创新项目)
2024.08: Excellent Intern at Huawei Technologies Co., Ltd.
2022.12: Ph.D. Student President’s Special Scholarship (博士研究生校长特别奖学金)

📚 Teaching

2025.09 - 2026.01, Teaching Assistant, LLM System and Engineering, Fall 2025, Nanjing University.
2025.03 - 2025.06, Teaching Assistant, Deep Learning Platform and Application, Spring 2025, Nanjing University.

💻 Internships

2026.07 - Present, Alibaba Group (Platform Technology, Intelligent Engine), Ali-Star Intern, Beijing. World-model inference frameworks.
2025.09 - 2026.07, Tencent (TEG, Network Platform Dept.), Rhino-Bird Intern, Beijing. MoE inference optimization.
2023.08 - 2025.04, Huawei (Computing Product Line), AI Infra Intern, Hangzhou. Modeling and system optimization for large-model training.
2021.07 - 2021.09, Alibaba Cloud (Open Platform), Backend Development Intern, Hangzhou. Backend development based on the Spring Boot framework.