SIGMOD 2026
Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search
Weijian Chen, Haotian Liu, Yangshen Deng, Long Xiang, Liang Huang, Gezi Li, Bo Tang
Edinburgh · ML · System
Yangshen Deng
Building scalable systems for Data & AI
YD
I am a first-year PhD student in the MLSys CDT at the University of Edinburgh, advised by Prof. Luo Mai and Prof. Edoardo M. Ponti. My work builds scalable systems for data and AI.
I received my bachelor’s degree from BUPT in 2022 and my master’s degree from SUSTech in 2025, where I worked in DBGroup with Prof. Bo Tang. I helped co-found AlayaDB.AI, and have interned at Ant Group, GaussDB Huawei, RS3Lab@EPFL, and Systems@TUDa.
News
Mar 2026
Our paper "AlayaLaser" about on-disk vector search is accepted by SIGMOD '26. We reveal the superising shift from I/O-bound to compute-bound. Click here to check how on-disk vector search can be faster than in-memory ones.
Apr 2025
Our paper "ParaGraph" is accepted by DaMoN '25 at SIGMOD.
Feb 2025
Our paper "AlayaDB" is accepted by SIGMOD '25 industry track. The first database for KV cache and attention.
Selected publications
DaMoN 2025
ParaGraph: Accelerating Graph Indexing through GPU-CPU Parallel Processing for Efficient Cross-modal ANNS
Yuxiang Yang, Shiwen Chen, Yangshen Deng, Bo Tang
SIGMOD 2025
AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference
Yangshen Deng, Zhengxin You, Long Xiang, Qilong Li, Peiqi Yuan, Zhaoyang Hong, Yitao Zheng, Wanting Li, Runzhong Li, Haotian Liu, Kyriakos Mouratidis, Man Lung Yiu, Huan Li, Qiaomu Shen, Rui Mao, Bo Tang
Mar 2026
Our paper "AlayaLaser" about on-disk vector search is accepted by SIGMOD '26. We reveal the superising shift from I/O-bound to compute-bound. Click here to check how on-disk vector search can be faster than in-memory ones.
Apr 2025
Our paper "ParaGraph" is accepted by DaMoN '25 at SIGMOD.
Feb 2025
Our paper "AlayaDB" is accepted by SIGMOD '25 industry track. The first database for KV cache and attention.
Jan 2025
I am awarded the BYD Scholarship.
Apr 2024
Our paper "How Does Software Prefetching Work on GPU Query Processing?" is accepted by DaMoN '24 at SIGMOD.
Mar 2024
Our paper "Accelerating Merkle Patricia Trie with GPU" is accepted by PVLDB '24.
Sep 2022
Our paper "GHive" is accepted by SoCC '22.
Feb 2022
Our paper "GHive" is accepted by SIGMOD '22 demo track.
SIGMOD 2026
Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search
Weijian Chen, Haotian Liu, Yangshen Deng, Long Xiang, Liang Huang, Gezi Li, Bo Tang
arXiv 2026
ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning
Jie Xiao, Meng Chen, Qingnan Ren, Jingwei Song, Jiaqi Huang, Yangshen Deng, Chris Tong, Wanyi Chen, Suli Wang, Ziqian Bi, Shuo Lu, Yiqun Duan, Xu Wang, Rymon Yu, Ween Yang, Lynn Ai, Eric Yang, Bill Shi
DaMoN 2025
ParaGraph: Accelerating Graph Indexing through GPU-CPU Parallel Processing for Efficient Cross-modal ANNS
Yuxiang Yang, Shiwen Chen, Yangshen Deng, Bo Tang
SIGMOD 2025
AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference
Yangshen Deng, Zhengxin You, Long Xiang, Qilong Li, Peiqi Yuan, Zhaoyang Hong, Yitao Zheng, Wanting Li, Runzhong Li, Haotian Liu, Kyriakos Mouratidis, Man Lung Yiu, Huan Li, Qiaomu Shen, Rui Mao, Bo Tang
arXiv 2025
NeuroTTT: Bridging Pretraining-Downstream Task Misalignment in EEG Foundation Models via Test-Time Training
Suli Wang, Yangshen Deng, Zhenghua Bao, Xinyu Zhan, Yiqun Duan
DaMoN 2024
How Does Software Prefetching Work on GPU Query Processing?
Yangshen Deng, Shiwen Chen, Zhaoyang Hong, Bo Tang
PVLDB 2024
Accelerating Merkle Patricia Trie with GPU
Yangshen Deng, Muxi Yan, Bo Tang
SoCC 2022
GHive: Accelerating Analytical Query Processing in Apache Hive via CPU-GPU Heterogeneous Computing
Haotian Liu, Bo Tang, Jiashu Zhang, Yangshen Deng, Xiao Yan, Xinying Zheng, Qiaomu Shen, Dan Zeng, Zunyao Mao, Chaozu Zhang, Zhengxin You, Zhihao Wang, Runzhe Jiang, Fang Wang, Man Lung Yiu, Huan Li, Mingji Han, Qian Li, Zhenghai Luo
SIGMOD 2022
GHive: A Demonstration of GPU-Accelerated Query Processing in Apache Hive
Haotian Liu, Bo Tang, Jiashu Zhang, Yangshen Deng, Xinying Zheng, Qiaomu Shen, Xiao Yan, Dan Zeng, Zunyao Mao, Chaozu Zhang, Zhengxin You, Zhihao Wang, Runzhe Jiang, Fang Wang, Man Lung Yiu, Huan Li, Mingji Han, Qian Li, Zhenghai Luo
Memories are the treasures in my life.