Yongjun He, Yao Lu, Gustavo Alonso
Deferred Continuous Batching in Resource-Efficient Large Language Model Serving
EuroMLSys 2024 Oral, Athens, Greece. [code]

Qiang Huang, Xin Wang, Susie Xi Rao, Zhichao Han, Zitao Zhang, Yongjun He, Quanqing Xu, Yang Zhao, Zhigao Zheng, Jiawei Jiang
BenchTemp: A General Benchmark for Evaluating Temporal Graph Neural Networks
ICDE 2024, Utrecht, Netherlands. [code]

Danrui Qi*, Jinglin Peng*, Yongjun He*, Jiannan Wang
Auto-FP: An Experimental Study of Automated Feature Preprocessing for Tabular Data
EDBT 2024 Experiments & Analysis Track, Paestum, Italy. [code]

Binhang Yuan*, Yongjun He*, Jared Quincy Davis, Tianyi Zhang, Tri Dao, Beidi Chen, Percy Liang, Christopher Ré, Ce Zhang
Decentralized Training of Foundation Models in Heterogeneous Environments
NeurIPS 2022 Oral, San Diego, CA, USA. [product]

Jue Wang*, Binhang Yuan*, Luka Rimanic*, Yongjun He, Tri Dao, Beidi Chen, Christopher Ré, Ce Zhang
Fine-tuning Language Models over Slow Networks using Activation Quantization with Guarantees
NeurIPS 2022, San Diego, CA, USA.

Xiangru Lian, Binhang Yuan, Xuefeng Zhu, Yulong Wang, Yongjun He, Honghuan Wu, Lei Sun, Haodong Lyu, Chengjun Liu, Xing Dong, Yiqiao Liao, Mingnan Luo, Congfei Zhang, Jingru Xie, Haonan Li, Lei Chen, Renjie Huang, Jianying Lin, Chengchun Shu, Xuezhong Qiu, Zhishan Liu, Dongying Kong, Lei Yuan, Hai Yu, Sen Yang, Ce Zhang, Ji Liu
Persia: An Open, Hybrid System Scaling Deep Learning Based Recommenders up to 100 Trillion Parameters
SIGKDD 2022 Applied Data Science Track, Washington, D.C., USA. [code]

Yongjun He
High-Performance In-Memory OLTP via Coroutine-to-Transaction
Master Thesis, School of Computing Science, Faculty of Applied Sciences, Simon Fraser University

Yongjun He, Jiacheng Lu, Tianzheng Wang
CoroBase: Coroutine-Oriented Main-Memory Database Engine
VLDB 2021, Copenhagen, Denmark. [code] [talk at VLDB 2021]

Alex Depoutovitch, Chong Chen, Jin Chen, Paul Larson, Shu Lin, Jack Ng, Wenlin Cui, Qiang Liu, Wei Huang, Yong Xiao, Yongjun He
Taurus Database: How to be Fast, Available, and Frugal in the Cloud
SIGMOD 2020, Portland, OR, USA. [product]

Pei Wang, Yongjun He, Ryan Shea, Jiannan Wang, Eugene Wu
Deeper: A Data Enrichment System Powered by Deep Web
SIGMOD 2018 Demo Track, Houston, TX, USA. [code] [demo video]