Xiaoxuan Liu

Xiaoxuan Liu

Auto-generated profile, based on publicly available information

Xiaoxuan Liu

UC Berkeley, Berkeley, California, USA

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 March 2025
Verified
Conference Paper
Open access
SCShiyi Cao
Shiyi Cao
SLShu Liu
Shu Liu
TGTyler Griggs
Tyler Griggs
PSPeter Schafhalter
Peter Schafhalter
XLXiaoxuan Liu
Xiaoxuan Liu
ISIon Stoica
Ion Stoica
Efficient deployment of large language models, particularly Mixture of Experts (MoE) models, on resource-constrained platforms presents significant challenges in terms of computational efficiency and memory utilization. The MoE architecture, renowned for its ability to increase model capacity without a proportional increase in inference cost, greatly reduces the token generation latency compared with dense models. However, the large model size makes MoE models inaccessible to individuals without high-end GPUs. In this paper, we propose a high-throughput MoE batch inference system, MoE-Lightning, that significantly outperforms past work. MoE-Lightning introduces a novel CPU-GPU-I/O pipelining schedule, CGOPipe, with paged weights to achieve high resource utilization, and a performance model, HRM, based on a Hierarchical Roofline Model we introduce to help find policies with higher throughput than existing systems. MoE-Lightning can achieve up to (10.3x) higher throughput than state-of-the-art offloading-enabled LLM inference systems for Mixtral 8x7B on a single T4 GPU (16GB). When the theoretical system throughput is bounded by the GPU memory, MoE-Lightning can reach the throughput upper bound with 2-3x less CPU memory, significantly increasing resource utilization. MoE-Lightning also supports efficient batch inference for much larger MoEs (e.g., Mixtral 8x22B and DBRX) on multiple low-cost GPUs (e.g., 2--4 T4s).

12 October 2025
Verified
Conference Paper
Open access
KDKuntai Du
Kuntai Du
BWBowen Wang
Bowen Wang
CZChen Zhang
Chen Zhang
YCYiming Cheng
Yiming Cheng
QLQing Lan
Qing Lan
JJJunchen Jiang
Junchen Jiang

12 October 2025
Verified
Conference Paper
Open access
CZChen Zhang
Chen Zhang
KDKuntai Du
Kuntai Du
SLShu Liu
Shu Liu
WKWoosuk Kwon
Woosuk Kwon
XMXiangxi Mo
Xiangxi Mo
ISIon Stoica
Ion Stoica

18 May 2026 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
QMQiuyang Mang
Qiuyang Mang
RHRunyuan He
Runyuan He
SZSuyang Zhong
Suyang Zhong
XLXiaoxuan Liu
Xiaoxuan Liu
HZHuanchen Zhang
Huanchen Zhang
ACAlvin Cheung
Alvin Cheung
Since 2020, automated testing for Database Management Systems (DBMSs) has flourished, uncovering hundreds of bugs in widely-used systems. A cornerstone of these techniques is test oracle , which typically implements a mechanism to generate equivalent query pairs, and subsequently runs the pair and identifies bugs by checking the consistency of their results. While running these oracles can be automated, designing the mechanism to generate equivalent queries remains a fundamentally manual endeavor. This paper explores the use of large language models (LLMs) to automate the discovery of equivalent queries in the design of test oracles, addressing a long-standing bottleneck towards fully automated DBMS testing. Although LLMs demonstrate impressive creativity, they are prone to hallucinations that can produce numerous false positive bug reports. Furthermore, their high monetary cost and latency mean that LLM invocations should be limited to ensure that bug detection is efficient and economical. To this end, we introduce Argus, a novel framework built upon the core concept of the Constrained Abstract Query —a SQL skeleton containing placeholders and their associated instantiation conditions, e.g., the placeholder must be filled by a Boolean column. Argus uses LLMs to generate pairs of these skeletons, with their equivalence formally proven using a SQL equivalence solver to ensure soundness. After that, the placeholders in the verified skeletons are instantiated with concrete, reusable SQL snippets that are also synthesized by LLMs to produce complex test cases. We have implemented Argus and evaluated it on five extensively tested DBMSs, discovering 41 previously unknown bugs, 36 of which are logic bugs, with 36 confirmed and 27 already fixed by the developers. The artifacts for Argus are available at https://github.com/joyemang33/Argus