Wentao Huang

My name is Wentao Huang (Chinese: 黄文韬). I am a final-year PhD candidate in the School of Computing, National University of Singapore, working under the supervision of Prof. Kian-Lee Tan and collaborating closely with Prof. Bingsheng He.

My research explores the art of data management through the lens of hardware-software co-design. I specialize in building high-performance data systems that fully exploit modern and emerging hardware (e.g., CXL, HBM). Broadly, my interests lie at the intersection of database systems, machine learning systems (MLSys), and high-performance computing.

[Google Scholar] [GitHub] [Twitter] [Mastodon] [CV]

Education

Ph.D. in Computer Science

Aug. 2020 - Present, National University of Singapore

M.Phil. in Computer Science

Sep. 2017 - Jun. 2020, Renmin University of China

B.S. in Electronic Engineering

Sep. 2013 - Jun. 2017, Shandong University

Internships

Research Engineer (Intern)

Jul. 2018 - Feb. 2019, Illinois Advanced Research Center at Singapore

Wentao Huang, Mian Lu, Kian-Lee Tan. Hash Joins Meet CXL: A Fresh Look.
16th Conference on Innovative Data Systems Research (CIDR), 2026.
[Paper] [Code] [Slides]

Wentao Huang, Mo Sha, Mian Lu, Yuqiang Chen, Bingsheng He, Kian-Lee Tan. Bandwidth Expansion via CXL: A Pathway to Accelerating In-Memory Analytical Processing. 15th International Workshop on Accelerating Analytics and Data Management Systems Using Modern Processor and Storage Architectures (ADMS), 2024.
[Paper] [Code] [Slides] [中文博客]

Yunhong Ji, Wentao Huang, Xuan Zhou. HeterMM: applying in-DRAM index to heterogeneous memory-based key-value stores. Frontiers of Computer Science (FCS), 18(4): 184612, 2024.
[Paper]

Yunhong Ji, Wentao Huang, Xuan Zhou, Bingsheng He, Kian-Lee Tan. TaC: An Anti-Caching Key-Value Store on Heterogeneous Memory Architectures. 27th International Conference on Extending Database Technology (EDBT), 2024.
[Paper] [Code] [Slides]

Wentao Huang, Yunhong Ji, Xuan Zhou, Bingsheng He, Kian-Lee Tan. A Design Space Exploration and Evaluation for Main-Memory Hash Joins in Storage Class Memory. 49th International Conference on Very Large Data Bases (VLDB), 2023.
[Paper] [Technical Report] [Code] [Slides] [Video]

Wentao Huang, Yuchen Li, Yuan Fang, Ju Fan, Hongxia Yang. BiANE: Bipartite Attributed Network Embedding. 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2020.
[Paper] [Supplementary] [Code] [Slides] [Video] [中文概述]

Apache SINGA

Architected the generative adversarial networks (GANs) module for Apache SINGA, a top-level open-source library designed for scalable, distributed deep learning across heterogeneous hardware backends, with specialized optimizations for healthcare-centric AI workloads.

• Email: huangwentaochina@gmail.com
• Address: COM1-01-08, 13 Computing Drive, Singapore, 117417