Zhibin Wang
王智彬

---

中文点这里

Biography

I am an Assistant Professor in the Software Institute, Nanjing University. I am also a member of NASA and COSEC. I received my Ph.D. degree in School of Computer Science, Nanjing University, advised by Prof. Chen Tian and Prof. Sheng Zhong. My current research focus is on AI Infra, including efficient training, serving, and kernel optimization for large language models. Related research has been published in top-tier conferences, such as SIGMOD, PPoPP, HPDC, and ATC. As the first author, I have published Nanjing University’s first SIGMOD, PPoPP, and HPDC papers.

Prospective Students

We are looking for self-motivated students who are interested in AI Infra. We welcome students with strong algorithmic, mathematical, and programming skills. Please contact me by email with your CV.

Please select the Software Institute (软件学院) when applying. I was previously affiliated with the School of Intelligent Software and Engineering (智能软件与工程学院), so please be careful not to select the wrong school.

Education & Experience

Publications

1. HPDC 2026 Zhibin Wang, Zetao Hong, Xue Li, Zibo Wang, Shipeng Li, Qingkai Meng, Qing Wang, Chengying Huan, Rong Gu, Sheng Zhong, Chen Tian. STAR: Decode-Phase Rescheduling for LLM Inference.

2. HPDC 2026 Chengying Huan, Ziheng Meng, Zhengyi Yang, Yongchao Liu, Jie Zhang, Qing Wang, Jing Wang, Shaonan Ma, Zhibin Wang, Mingxing Zhang, Rong Gu, Baokun Wang, Guihai Chen, Chen Tian. BCCE: Block-Centric GPU Co-Design for Real-Time Range-Top-K Query at Scale.

3. SIGMOD 2026 Zhibin Wang, Rui Ning, Chao Fang, Zhonghui Zhang, Xi Lin, Shaobo Ma, Mo Zhou, Xue Li, Zhongfeng Wang, Chengying Huan, Rong Gu, Kun Yang, Guihai Chen, Sheng Zhong, Chen Tian. CoDec: Prefix-Shared Decoding Kernel for LLMs.

4. SIGMOD 2026 Chengying Huan, Renjie Yao, Shaonan Ma, Rong Gu, Zhengyi Yang, Lizheng Chen, Zhibin Wang, Mingxing Zhang, Fang Xi, Guihai Chen, Chen Tian. CMANNS: GPU-Accelerated Graph Index Construction for ANNS via Compute–Memory Disaggregation.

5. DAC 2026 Zibo Wang, Yuhang Zhou, Zhibin Wang (corresponding author), Shipeng Li, Xinjing Huang, Chendong Cai, Bingxu Mu, Yuqing Sun, Zhiheng Hu, Bin She, Shu You, Guanghuan Fang, Rong Gu, Wanchun Dou, Guihai Chen and Chen Tian. SmartSwap: Swap-Based Memory Optimization for LLM Training under Varying Operator Sequences.

6. INFOCOM 2026 Yuhang Zhou, Zhibin Wang (corresponding author), Peng Jiang, Haoran Xia, Junhe Lu, Qianyu Jiang, Rong Gu, Hengxi Xu, Xinjing Huang, Guanghuan Fang, Zhiheng Hu, Jingyi Zhang, Yongjin Cai, Jian He, Chen Tian. Chameleon: Adaptive Fault Tolerance for Distributed Training via Real-time Policy Selection.

7. SIGMOD 2026 Yuhang Li, Rong Gu, Chengying Huan, Zhibin Wang, Renjie Yao, Chen Tian, Guihai Chen. HotPrefix: Hotness-Aware KV Cache Scheduling for Efficient Prefix Sharing in LLM Inference Systems

8. PVLDB 2025 Minze Xu, Zhentai Xie, Zhibin Wang, Guangzhan Wang, Longbin Lai, Yuan Zhang, Chen Tian, Sheng Zhong. Sectric: Towards Accurate, Privacy-preserving and Efficient Triangle Counting.

9. ATC 2025 Yuhang Zhou, Zibo Wang, Zhibin Wang (corresponding author), Ruyi Zhang, Chen Tian, Xiaoliang Wang, Wanchun Dou, Guihai Chen, Bingqiang 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. Accelerating Model Training on Ascend Chips: An Industrial System for Profiling, Analysis and Optimization

10. ASPLOS 2025 Yuhang Zhou, Zhibin Wang (corresponding author), 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. Squeezing Operator Performance Potential for the Ascend Architecture. Wechat Blog

11. EuroSys 2025 Pinhuan Wang, Chengying Huan, Zhibin Wang, Chen Tian, Yuede Ji, Hang Liu. BINGO: Radix-based Bias Factorization for Random Walk on Dynamic Graphs.

12. PPoPP 2025 Zhibin Wang, Xi Lin, Xue Li, Pinhuan Wang, Ziheng Meng, Hang Liu, Chen Tian, Sheng Zhong. Swift Unfolding of Communities: GPU-Accelerated Louvain Algorithm. Wechat Blog

13. PVLDB 2025 Xue Li, Weibin Zeng, Zhibin Wang, Diwen Zhu, Jingbo Xu, Wenyuan Yu, Jingren Zhou. GraphAr: An Efficient Storage Scheme for Graph Data in Data Lakes.

14. HPEC 2024 Ketai Zhao, Yuhang Zhou, Hongxu Pan, Zhibin Wang (corresponding author), Sheng Zhong and Chen Tian. Sans: Streaming Anonymized Network Sensing.

15. VLDBJ 2024 Zhibin Wang, Longbin Lai, Yixue Liu, Bing Shui, Chen Tian, Sheng Zhong. Parallelization of Butterfly Counting on Hierarchical Memory.

16. HPEC 2023 Zhibin Wang, Ziheng Meng, Xue Li, Xi Lin, Long Zheng, Chen Tian, and Sheng Zhong. SMOG: Accelerating Subgraph Matching on GPUs. Awarded Graph Challenge Champion.

17. ATC 2023 Longbin Lai, Yufan Yang, Zhibin Wang, Yuxuan Liu, Haotian Ma, Sijie Shen, Bingqing Lyu, Xiaoli Zhou, Wenyuan Yu, Zhengping Qian, Chen Tian, Sheng Zhong, Yeh-Ching Chung, Jingren Zhou. GLogS: Interactive Graph Pattern Matching Query At Large Scale.

18. SIGMOD 2023 Zhibin Wang, Longbin Lai, Yixue Liu, Bing Shui, Chen Tian, Sheng Zhong. I/O-Efficient Butterfly Counting at Scale.

19. TPDS 2021 Santosh Pandey, Zhibin Wang (co-first author), Sheng Zhong, Chen Tian, Bolong Zheng, Xiaoye Li, Lingda Li, Adolfy Hoisie, Caiwen Ding, Dong Li, Hang Liu. TRUST: Triangle Counting Reloaded on GPUs.

Preprints

• ArXiv Zetao Hong, Song Yuan, Yuanhao Ding, Yibo Zhu, Daxin Jiang, Zhibin Wang (corresponding author), Chen Tian. Scheduling Mixed RL Rollouts Beyond Prefix Locality

• ArXiv Qianggang Ding, Xingyao Wang, Rui Feng, Zhibin Wang, Feixiang Wang, Kelong Mao, Hao Sun, Zhiyao Luo, Jiankai Tang, Lei Li, Jiadong Guo, Minheng Ni, Weicong Lin, Chenxi Yang, Hongxiang Gao, Zhenghua Chen, Yang Bai, Min Wu, Jun Cheng, Huazhu Fu, Dacheng Tao, Bang Liu. ComBodied Agents: a New Paradigm of Human-Centric Agentic AI

• ArXiv Yikai Wang, Chuansai Zhou, Yuhang Zhou, Weiqiang Wu, Cong Wu, Yue Deng, Ben Feng, Mingming Zhu, Beirong Zhou, Zhibin Wang (corresponding author), Sheng Zhong, Chen Tian, Wangze Zhang. MoE Proxy Models for Low-Cost Failure Reproduction and Diagnosis in LLM RL Post-Training

• ArXiv Yuhang Zhou, Peng Jiang, Qianyu Jiang, Zhibin Wang (corresponding author), Xinghui Tian, Jianwei Zhou, Songxiang Zhu, Jingyi Zhang, Junsong Wang, Chen Tian. Adaptive Matrix Multiplication for Dynamic Shapes on Ascend NPUs

• ArXiv Chengying Huan, Yubo Wang, Pinhuan Wang, Lizheng Chen, Jie Zhang, Fangxin Liu, Qing Wang, Ruixuan Liu, Shaonan Ma, Mingxing Zhang, Zhibin Wang, Rong Gu, Guihai Chen, Chen Tian. TIDE-MC: Two-Sided Interpolative Decomposition for Billion-Scale GPU Matrix Completion

• ArXiv Zhibin Wang, Xuying Han, Zhaohua Yang, Fuliang Liu, Xue Li, Rong Gu, Sheng Zhong, Chen Tian. SpecLA: Efficient Speculative Decoding for Linear-Attention Models

• ArXiv Zhibin Wang, Ziyu Zhong, Nuo Shen, Yuhang Zhou, Rong Gu, Sheng Zhong. SSV: Sparse Speculative Verification for Efficient LLM Inference

• ArXiv Fuliang Liu, Xue Li, Ketai Zhao, Yinxi Gao, Ziyan Zhou, Zhonghui Zhang, Zhibin Wang (corresponding author), Wanchun Dou, Sheng Zhong, Chen Tian. DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference

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

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

• ArXiv Zhibin Wang, Shipeng Li, Yuhang Zhou, Xue Li, Zhonghui Zhang, Nguyen Cam-Tu, Rong Gu, Chen Tian, Guihai Chen, Sheng Zhong. Revisiting Service Level Objectives and System Level Metrics in Large Language Model Serving.

• ArXiv Hongxu Pan, Shuxian Hu, Mo Zhou, Zhibin Wang (corresponding author), Rong Gu, Chen Tian, Kun Yang, Sheng Zhong Chordless Structure: A Pathway to Simple and Expressive GNNs

• ArXiv Tao He, Xue Li, Zhibin Wang, Kun Qian, Jingbo Xu, Wenyuan Yu, Jingren Zhou. Unicron: Economizing self-healing llm training at scale.

Honors & Awards

• 2015 Gold Medal, ACM-ICPC Asia Regional Contest

• 2015 China National Scholarship

• 2016 Outstanding Undergraduate Award, CCF(China Computer Federation)

• 2023 Outstanding Research intern, Alibaba

Teaching

• 深度学习平台和应用（2026春）
• 大模型系统与工程（2025秋）
• 数据结构与算法（2025秋）
• 深度学习平台和应用（2025春）