Xiyuan Zhang


Scientist @ AWS AI

Ph.D. @ University of California, San Diego

xiyuanz [AT] amazon.com

Bio

I am a scientist at AWS AI. I earned my Ph.D. degree in CS at UC San Diego, where I am fortunate to be advised by Professor Rajesh Gupta and Professor Jingbo Shang. I received my B.S. degree in CS with honors from Chu Kochen Honors College, Zhejiang University.

My research interests lie in machine learning for sequential data (NLP, time series, spatiotemporal), with practical impact including healthcare, IoT, climate science, smart city and e-commerce.

Publications

UniMTS: Unified Pre-training for Motion Time Series

Xiyuan Zhang, Diyan Teng, Ranak Roy Chowdhury, Shuheng Li, Dezhi Hong, Rajesh K. Gupta, Jingbo Shang

NeurIPS 2024

Chronos: Learning the Language of Time Series

Abdul Fatir Ansari, Lorenzo Stella, Caner Turkmen, Xiyuan Zhang, Pedro Mercado, Huibin Shen, Oleksandr Shchur, Syama Sundar Rangapuram, Sebastian Pineda Arango, Shubham Kapoor, Jasper Zschiegner, Danielle C. Maddix, Michael W. Mahoney, Kari Torkkola, Andrew Gordon Wilson, Michael Bohlke-Schneider, Yuyang Wang

TMLR (100MM+ downloads in six months)

Large Language Models for Time Series: A Survey

Xiyuan Zhang, Ranak Roy Chowdhury, Rajesh Gupta, Jingbo Shang

IJCAI 2024, Survey Track

Unleashing the Power of Shared Label Structures for Human Activity Recognition

Xiyuan Zhang, Ranak Roy Chowdhury, Jiayun Zhang, Dezhi Hong, Rajesh Gupta, Jingbo Shang

CIKM 2023

Physics-Informed Data Denoising for Real-Life Sensing Systems

Xiyuan Zhang, Xiaohan Fu, Diyan Teng, Chengyu Dong, Keerthivasan Vijayakumar, Jiayun Zhang, Ranak Roy Chowdhury, Junsheng Han, Dezhi Hong, Rashmi Kulkarni, Jingbo Shang, Rajesh Gupta

SenSys 2023

Navigating Alignment for Non-Identical Client Class Sets: A Label Name-Anchored Federated Learning Framework

Jiayun Zhang, Xiyuan Zhang, Xinyang Zhang, Dezhi Hong, Rajesh Gupta, Jingbo Shang

KDD 2023

Towards Diverse and Coherent Augmentation for Time-Series Forecasting

Xiyuan Zhang, Ranak Roy Chowdhury, Jingbo Shang, Rajesh Gupta, Dezhi Hong

ICASSP 2023

Async-HFL: Efficient and Robust Asynchronous Federated Learning in Hierarchical IoT Networks

Xiaofan Yu, Ludmila Cherkasova, Harsh Vardhan, Quanling Zhao, Emily Ekaireb, Xiyuan Zhang, Arya Mazumdar, Tajana Šimunić Rosing

IoTDI 2023

PrimeNet: Pre-training for Irregular Multivariate Time Series

Ranak Roy Chowdhury, Jiacheng Li, Xiyuan Zhang, Dezhi Hong, Rajesh Gupta, Jingbo Shang

AAAI 2023

First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting

Xiyuan Zhang, Xiaoyong Jin, Karthick Gopalswamy, Gaurav Gupta, Youngsuk Park, Xingjian Shi, Hao Wang, Danielle C. Maddix, Yuyang Wang

NeurIPS 2022 All Things Attention Woskshop

Task-Aware Reconstruction for Time-Series Transformer

Ranak Roy Chowdhury, Xiyuan Zhang, Dezhi Hong, Rajesh Gupta, Jingbo Shang

KDD 2022

ESC-GAN: Extending Spatial Coverage of Physical Sensors

Xiyuan Zhang, Ranak Roy Chowdhury, Jingbo Shang, Rajesh Gupta, Dezhi Hong

WSDM 2022 (Oral)

Filling Conversation Ellipsis for Better Social Dialog Understanding

Xiyuan Zhang, Chengxi Li, Dian Yu, Samuel Davidson, Zhou Yu

AAAI 2020

Neural Embeddings for Nearest Neighbor Search Under Edit Distance

Xiyuan Zhang, Yang Yuan, Piotr Indyk

Awards

CPS Rising Stars, 2023
Qualcomm Innovation Fellowship, 2022
Outstanding Graduate of Zhejiang University & Zhejiang Province
Distinguished Undergraduate Dissertation Award, Zhejiang University

Services

Conference Reviewer: ICML'23'24, NeurIPS'23'24 (Top Reviewer), ICLR'24'25, AAAI'23'24'25, WWW'24, ICASSP'24
Journal Reviewer: International Journal of Forecasting (IJF), ACM Transactions on Intelligent Systems and Technology (TIST)
Workshop Reviewer: NeurIPS'24 TSALM Workshop

Teaching: TA for CSE 151A: Introduction to Machine Learning, volunteer teacher for middle school students

Acknowledgement

This website design is based on the template from Martin Saveski.