I am an associate professor in the School of Computer Science and Engineering, Beihang University (BUAA). I was a postdoc researcher in the Department of Computer Science and Technology, Tsinghua University. I received my PhD degree from Tsinghua University in 2022 (advised by Professor Jiwu Shu and Youyou Lu), and Bachelor degree from Huazhong University of Science and Technology (HUST) in 2017.
My research interests are primarily in storage systems and AI systems, focusing on enhancing their performance and reliability. My work has been published in top-tier conferences and journals on computer systems, including OSDI, SOSP, FAST, USENIX ATC, EuroSys, ASPLOS, HPCA, DAC, MICRO and ACM TOS.
⭐ We are seeking self-motivated Master, PhD, and undergraduate students with strong programming skills to join our research in computer systems and architectures. If you’re interested, feel free to reach out with your CV.
🔥 News
- 🎉 July 2025. Amove (SW/HW codesign of LLM) has been accepted to MICRO’25.
- 🎉 Apr 2025. SpanTrain (AI training system) has been accepted to J-BDR.
- 🎉 Feb 2025. CaMDN (AI accelerator) has been accepted to DAC’25.
- 🎉 Jan 2025. CoServe (AI inference system) has been accepted to ASPLOS’25.
- 🎉 Nov 2024. Zebra (ZNS SSD RAID) has been accepted to HPCA’25.
- 🎉 August 2024. I will join Beihang University as an associate professor.
🔍 Research Topics
- I/O Stack and File System on Modern/Future Storage Devices (e.g., NVMe and CXL SSD)
- Consistency and Reliability: HORAE (OSDI’20), ccNVMe (SOSP’21)
- Concurrency and Scalability: MAX (USENIX ATC’21)
- Computational Storage (Smart SSD): λ-IO (FAST’23)
- Distributed and Networked Storage System on Fast Network Devices (e.g., RDMA NIC and DPU)
- Disaggregated Storage (NVMe-oF): RIO (EuroSys’23), ccNVMe-oF (ACM TOS), Volley (EuroSys’24)
- Distributed File System: SuperFS (#1 in the IO500 10-node Metadata Challenge, SC’22), SingularFS (USNNIX ATC’23)
- RDMA-based Storage: TeRM (FAST’24, ACM TOS)
- Efficient and Scalable Computer System and Architecture for New Applications (e.g., AI and LLM)
- AI Inference/Serving System: CoServe (ASPLOS’25), PipeBoost
- AI Training System: DeepCEE
- AI Accelerator: CaMDN (DAC’25), Amove (MICRO’25)
📝 Selected Publications
(✉: corresponding authors, #: co-first authors)
📰 Conference Papers
[MICRO’25] Amove: Accelerating LLMs through Mitigating Outliers and Salient Points via Fine-Grained Grouped Vectorized Data Type
Xilong Xie, Liang Wang, Limin Xiao, Meng Han, Lei Liu, Xiangrong Xu, Jinquan Wang, Zhen Song, Xiaojian Liao
Proceedings of the 58th IEEE/ACM International Symposium on Microarchitecture (MICRO 2025), (CCF-A)
[DAC’25] CaMDN: Enhancing Cache Efficiency for Multi-tenant DNNs on Integrated NPUs
Tianhao Cai, Liang Wang, Limin Xiao, Meng Han, Zeyu Wang, Lin Sun, Xiaojian Liao
Proceedings of the 61st ACM/IEEE Design Automation Conference (DAC 2025), (CCF-A)
[ASPLOS’25] CoServe: Efficient Collaboration-of-Experts (CoE) Model Inference with Limited Memory
Jiashun Suo, Xiaojian Liao✉, Limin Xiao✉, Li Ruan, Jinquan Wang, Xiao Su, Zhisheng Huo
Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2 (ASPLOS 2025), (CCF-A)
[HPCA’25] Zebra: Efficient Redundant Array of Zoned Namespace SSDs Enabled by Zone Random Write Area (ZRWA)
Tianyang Jiang, Guangyan Zhang, Xiaojian Liao, Yuqi Zhou
Proceedings of the 31st IEEE International Symposium on High-Performance Computer Architecture (HPCA 2025), (CCF-A)
[EuroSys’24] Volley: Accelerating Write-Read Orders in Disaggregated Storage
Shaoxun Zeng, Xiaojian Liao, Hao Guo, Youyou Lu
Proceedings of the Nineteenth European Conference on Computer Systems (EuroSys 2024), (CCF-A)
[FAST’24] TeRM: Extending RDMA-Attached Memory with SSD
Zhe Yang, Qing Wang, Xiaojian Liao, Youyou Lu, Keji Huang, Jiwu Shu
Proceedings of the 22nd USENIX Conference on File and Storage Technologies (FAST 2024), (CCF-A)
Invited for fast-tracked publication in ACM Transactions on Storage
[USENIX ATC’23] SingularFS: A Billion-Scale Distributed File System Using a Single Metadata Server
Hao Guo, Youyou Lu, Wenhao Lv, Xiaojian Liao, Shaoxun Zeng, Jiwu Shu
Proceedings of 2023 USENIX Annual Technical Conference (USENIX ATC 2023), (CCF-A)
[FAST’23] λ-IO: A Unified IO Stack for Computational Storage
Zhe Yang, Youyou Lu, Xiaojian Liao, Youmin Chen, Junru Li, Siyu He, Jiwu Shu
Proceedings of the 21st USENIX Conference on File and Storage Technologies (FAST 2023), (CCF-A)
[EuroSys’23] RIO: Order-Preserving and CPU-Efficient Remote Storage Access
Xiaojian Liao, Zhe Yang, Jiwu Shu
Proceedings of the 18th European Conference on Computer Systems (EuroSys 2023), (CCF-A)
[SOSP’21] Crash Consistent Non-Volatile Memory Express
Xiaojian Liao, Youyou Lu, Zhe Yang, Jiwu Shu
Proceedings of the 28th ACM Symposium on Operating Systems Principles (SOSP 2021), (CCF-A)
[USENIX ATC’21] Max: A Multicore-Accelerated File System for Flash Storage
Xiaojian Liao, Youyou Lu, Erci Xu, Jiwu Shu
Proceedings of 2021 USENIX Annual Technical Conference (USENIX ATC 2021), (CCF-A)
[OSDI’20] Write Dependency Disentanglement with HORAE
Xiaojian Liao, Youyou Lu, Erci Xu, Jiwu Shu
Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2020), (CCF-A)
📖 Journal Papers
[大数据] SpanTrain: A Cross-Domain Distributed Model Training System for Cloud-Edge-End Heterogeneous Devices
Jinquan Wang, Xuzhao Liu, Xiaojian Liao✉, Limin Xiao✉, Zhisheng Huo, Jiashun Suo, Yuntong Li, Runnan Shen, Xilong Xie, Xicheng Tang
Journal of BIG DATA RESEARCH (大数据 in Chinese), 2025, (CCF-T2)
[ACM TOS’25] Efficiently Enlarging RDMA-Attached Memory with SSD
Zhe Yang, Qing Wang, Xiaojian Liao, Youyou Lu, Keji Huang, Jiwu Shu
ACM Transactions on Storage (ACM TOS 2025), Volume 21, Issue 2, (CCF-A), Fast-Tracked
[ACM TOS’23] Efficient Crash Consistency for NVMe over PCIe and RDMA
Xiaojian Liao, Youyou Lu, Zhe Yang, Jiwu Shu
ACM Transactions on Storage (ACM TOS 2023), Volume 19, Issue 1, (CCF-A)
[中国科学: 信息科学] Progress on Storage Systems for Disaggregated Data Centers
Jiwu Shu, Youmin Chen, Qing Wang, Jing Wang, Junru Li, Xiaojian Liao
SCIENTIA SINICA Informationis (中国科学: 信息科学, In Chinese), 2023, (CCF-T1)
[计算机研究与发展] A Low-Latency Storage Engine with Low CPU Overhead
Xiaojian Liao, Zhe Yang, Hongzhang Yang, Yaofeng Tu, Jiwu Shu
Journal of Computer Research and Development (计算机研究与发展, in Chinese), 2023, (CCF-T1)
✍️ Preprint
PipeBoost: Resilient Pipelined Architecture for Fast Serverless LLM Scaling
Chongpeng Liu, Xiaojian Liao✉, Hancheng Liu, Limin Xiao, Jianxin Li✉
DeepCEE: Efficient Cross-Region Model Distributed Training System under Heterogeneous GPUs and Networks
Jinquan Wang#, Xiaojian Liao#, Xuzhao Liu, Jiashun Suo, Zhisheng Huo, Chenhao Zhang, Xiangrong Xu, Runnan Shen, Xilong Xie, Limin Xiao
🏅 Selected Honors & Awards
- 2022, SuperFS ranked #1 in the IO500 10-node Metadata Challenge, SC’22
- 2022, ACM SIGOPS ChinaSys Doctoral Dissertation Award
- 2022, Shuimu Tsinghua Scholar (清华大学水木学者)
- 2022, Distinguished Doctoral Graduate of Tsinghua University (清华大学优秀博士毕业生, 5 PhDs in CS department)
- 2022, Distinguished Doctoral Dissertation Award of Tsinghua University (清华大学优秀博士学位论文, 9 PhDs in CS department)
- 2021, First Prize of Shenzhen Science and Technology Improvement Award （深圳市科技进步奖一等奖）
- 2021, Zhong Shimo Scholarship (清华计算机系钟士模奖学金, the highest honour of CS students of Tsinghua, 4 postgraduate students)
- 2021, First Prize of 1984 Innovation Scholarship (only 1 project was awarded)
- 2020, ByteDance Scholars Program (10 students nationwide were selected)
🕑 Professional Services
- 2024-2025, Journal Reviewer of IEEE Transactions on Computers
- 2024, Program committee of the 26th ACM SIGOPS ChinaSys workshop
- 2023, Program committee of the 10th ACM Eurosys PaPoc workshop
- 2022, Journal reviewer of IEEE Transactions on Cloud Computing