Yiyuan Yang · 杨毅远
About News Research Background Publications Projects Awards Service Talks

About Me

Yiyuan Yang is a D.Phil. (Ph.D.) student and Clarendon Scholar in the Department of Computer Science at the University of Oxford, specializing in data mining, time series, audio/speech, signal processing, and large language models. He holds a master's degree from the Department of Automation at Tsinghua University and a bachelor's degree from the School of Artificial Intelligence and Automation (Innovation Honors Class) and Qiming College at Huazhong University of Science and Technology. He has also interned at the Microsoft Applied Sciences Group, Microsoft Research, and Alibaba DAMO Academy.

Yiyuan is an avid open-source contributor, with projects amassing over 37,000 GitHub stars. He has authored three books based on his tutorials — two of them bestsellers — and published over 40 papers in top journals and conferences, including TKDE, CSUR, KDD, NeurIPS, ACL, AAAI, IJCAI, TNNLS, CIKM, ICASSP, and Interspeech, with over 2,000 citations. He also serves as a reviewer for leading journals and conferences, including TPAMI, TKDE, TKDD, TIFS, TOS, TNNLS, TOMM, TCYB, TCSVT, TII, IoT, SPL, TITS, Neurocomputing, NeurIPS, KDD, WWW, AAAI, ACL, and SDM. In his free time, Yiyuan enjoys singing and playing various sports.

2,000+Citations 40+Publications 17h-index 37,000+GitHub Stars

News

2026.08📣 I am on the job market! Open to Assistant Professor positions in academia and Research Scientist / Applied Scientist roles in industry — feel free to reach out!
2026.08🎓 Milestone: Completed my D.Phil. (Ph.D.) viva at the University of Oxford!
2026.08📢 Presented our hands-on tutorial End-to-End Learning for Partially-Observed Time Series with PyPOTS at KDD 2026 in Jeju, Korea.
2026💼 I will be joining the Superintelligence Lab at Meta (Bellevue, WA) as a Research Scientist Intern, working on speech/audio and multimodal LLMs — start date to be confirmed.
2026.07🏆 Award: Chinese Government Award for Outstanding Self-financed Students Abroad — Class A Special Excellence (国家优秀自费留学生奖学金·特别优秀奖), China Scholarship Council.
2026.06🏆 Award: Named one of the Most Anticipated Academic Rising Stars (最受瞩目学术新星) at BAAI QingYuan InnoVibe 2026. [Link]
2026.06📄 Geometry-Informed Distributed Acoustic Scene Understanding accepted at Interspeech 2026.
2026.04📄 Time-RA (time series reasoning with LLM feedback) accepted to the Findings of ACL 2026.
2026.04💼 Joined the Applied Sciences Group at Microsoft as an Applied Scientist Intern (Apr – Jul 2026).
2026.02🏆 Award: Our fiddler-crab bioacoustics study in the Journal of Experimental Biology was shortlisted for the JEB Outstanding Paper Prize 2025.
2025.09📄 Two papers accepted at NeurIPS 2025: ScatterAD and Target Speaker Extraction.
2025.06💼 Research internship at Microsoft Research on adaptive speech separation in conversational scenarios (Jun – Aug 2025).
2025.05📄 Time-MQA accepted at ACL 2025 (main conference), our multivariate time-series imputation survey at IJCAI 2025, and Efficient and Microphone-Fault-Tolerant 3D Sound Source Localization at Interspeech 2025.
2024.12📚 Our book 深度学习详解 (LeeDL-Tutorial) was selected as one of JD's 2024 Annual Best Books (overall Top 50) and a PTP Excellent New Book of 2024.

Research Interests

Currently, I focus on the following research topics:

Spatio-Temporal Data Mining

Spatio-temporal data mining and signal processing for real-world sensing systems.

Time Series & LLMs

Time-series analysis, anomaly detection, and reasoning with large language models.

Audio & Multimodal Learning

Acoustic scene understanding, speech enhancement, separation, and localization, and audio-centric multimodal learning.

Real-World AI Deployment

Deploying algorithms in real-world applications — efficient, robust, and fault-tolerant models for industrial sensing, monitoring, and production AI systems.

I love collaborating with others! If you're interested in working together, feel free to reach out — don't hesitate! 😊

Education & Experience

Education

Internships & Exchange

  • Incoming · 2026
    Research Scientist Intern, Superintelligence Lab, Meta
    Speech/audio and multimodal LLMs · Bellevue, WA, USA · start date to be confirmed
  • 2026.04 – 2026.07
    Applied Scientist Intern, Applied Sciences Group, Microsoft
    Supervised by Dr. Eric Sommerlade · LLM-driven code generation that automatically produces explanatory videos · Reading, UK
  • 2025.06 – 2025.08
    Research Intern, Applied Sciences Group, Microsoft Research
    Supervised by Dr. Soumitro Chakrabarty · Adaptive speech separation in conversational scenarios · Munich, Germany
  • 2022.10 – 2023.02
    Research Intern, Alibaba DAMO Academy, Decision Intelligence Lab
    Supervised by Dr. Qingsong Wen and Dr. Liang Sun · Time-series anomaly detection — work that led to a granted patent and the DCdetector paper (KDD 2023) · Hangzhou, China
  • 2019.01 – 2019.02
    Exchange Student, University of Cambridge

Selected Publications

Full list on my Google Scholar profile.

Conference Papers 19 entries

  • 19

    Geometry-Informed Distributed Acoustic Scene Understanding

    Y. Yang, S. Xu, N. Trigoni, A. Markham

    Interspeech 2026
  • 18

    End-to-End Learning for Partially-Observed Time Series with PyPOTS

    W. Du, Y. Yang, T. Zhan, Q. Wen

    KDD Tutorial 2026
  • 17

    Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback

    Y. Yang, Z. Liu, L. Song, K. Ying, Z. Wang, T. Bamford, S. Vyetrenko, J. Bian, Q. Wen

    ACL Findings 2026 ArXiv Code Dataset
  • 16

    ScatterAD: Temporal-Topological Scattering Mechanism for Time Series Anomaly Detection

    T. Yin, S. Fu, Z. Zhang, L. Huang, X. Zhang, Y. Yang, K. Yang, M. Yan

    NeurIPS 2025 Link
  • 15

    Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollments

    S. Xu, Y. Yang, N. Trigoni, A. Markham

    NeurIPS 2025 ArXiv
  • 14

    OxBioZ: Wearable Continuous Bioimpedance Monitoring System and Multi-Activity Dataset with Physiological and Motion Signals

    X. Hou, Y. Yang, J. Beuchert, H. Kayan, Q. Xie, K. T. Ly, Q. Deng, N. Pham, A. Markham, N. Trigoni

    ACM SmartWear Workshop 20253rd ACM Workshop on Smart Wearable Systems and Applications, co-located with ACM MobiCom Link
  • 13

    Efficient and Microphone-Fault-Tolerant 3D Sound Source Localization

    Y. Yang, S. Xu, N. Trigoni, A. Markham

    Interspeech 2025 ArXiv
  • 12

    Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement

    Y. Kong*, Y. Yang*, Y. Hwang, W. Du, S. Zohren, Z. Wang, M. Jin, Q. Wen

    ACL Main 2025 ArXiv Dataset
  • 11

    Deep Learning for Multivariate Time Series Imputation: A Survey

    J. Wang, W. Du, Y. Yang, L. Qian, W. Cao, K. Zhang, W. Wang, Y. Liang, Q. Wen

    IJCAI 2025 Link GitHub Repo
  • 10

    Advancing Multivariate Time Series Anomaly Detection: A Comprehensive Benchmark with Real-World Data from Alibaba Cloud

    C. Zhang, Y. Zhang, L. Peng, Q. Wen, Y. Yang, C. Fan, M. Jiang, L. Fan, L. Sun

    CIKM 2024 Link Code Dataset
  • 9

    Pre-training Feature Guided Diffusion Model for Speech Enhancement

    Y. Yang, N. Trigoni, A. Markham

    Interspeech 2024 ArXiv
  • 8

    SSL-Net: A Synergistic Spectral and Learning-based Network for Efficient Bird Sound Classification

    Y. Yang, K. Zhou, N. Trigoni, A. Markham

    ICASSP 2024 ArXiv
  • 7

    AI-based Energy Transportation Safety: Pipeline Radial Threat Estimation using Intelligent Sensing System

    C. Zhu, Y. Yang, K. Yang, H. Zhang, Q. Yang, C. L. Philip Chen

    AAAI 2024 ArXiv
  • 6

    DynPoint: Dynamic Neural Point for View Synthesis

    K. Zhou, J. Zhong, S. Shin, K. Lu, Y. Yang, A. Markham, N. Trigoni

    NeurIPS 2023 ArXiv Code Poster
  • 5

    DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection

    Y. Yang, C. Zhang, T. Zhou, Q. Wen, L. Sun

    KDD 2023 ArXiv Code Video Poster Slides
  • 4

    SGDP: A Stream-Graph Neural Network Based Data Prefetcher

    Y. Yang, R. Li, Q. Shi, X. Li, G. Hu, X. Li, M. Yuan

    IJCNN 2023 ArXiv PDF Code Slides
  • 3

    Block Access Pattern Discovery via Compressed Full Tensor Transformer

    X. Li, Q. Shi, G. Hu, L. Chen, H. Mao, Y. Yang, M. Yuan, J. Zeng, Z. Cheng

    CIKM 2021 Link PDF
  • 2

    Pipeline Safety Early Warning Method for Distributed Signal using Bilinear CNN and LightGBM

    Y. Yang, Y. Li, H. Zhang

    ICASSP 2021 Link PDF Poster Slides Video
  • 1

    Early Safety Warnings for Long-Distance Pipelines: A Distributed Optical Fiber Sensor Machine Learning Approach

    Y. Yang, Y. Li, T. Zhang, Y. Zhou, H. Zhang

    AAAI 2021Oral Link PDF Poster

Journal Articles 12 entries

  • 12

    Enhanced Pipeline Radial Threat Monitoring System with Distributed Acoustic Sensing and Multi-View Information Fusion

    C. Zhu, Y. Pu, Y. Yang, Y. Ji, K. Li, X. Jiao

    Measurement · 2026Q1, IF = 5.6
  • 11

    Monitoring Landslide Disturbances using Distributed Acoustic Sensing under Extreme Weather Conditions

    C. Zhu, Y. Yang, K. Yang, W. Zhu, Q. Yang

    npj Natural Hazards · 2026Nature Portfolio
  • 10

    A Survey on Diffusion Models for Time Series and Spatio-Temporal Data

    Y. Yang, M. Jin, H. Wen, C. Zhang, Y. Liang, L. Ma, Y. Wang, C. Liu, B. Yang, Z. Xu, J. Bian, S. Pan, Q. Wen

    ACM Computing Surveys (CSUR) · 2025Q1, IF = 30.4 ArXiv GitHub Repo
  • 9

    Constraints on Percussive Seismic Signals in a Noisy Environment by European Fiddler Crabs, Afruca tangeri

    T. Mulder, Y. Yang, E. Morley, T. E Miller, D. Hending, G. K Taylor, B. Mortimer

    Journal of Experimental Biology (JEB) · 2025IF = 3.0★ JEB Outstanding Paper Prize (Shortlisted) 2025 Paper
  • 8

    PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly Detection

    Z. Zhong, Z. Yu, Y. Yang, W. Wang, K. Yang

    IEEE Transactions on Big Data · 2025Q1, IF = 5.7 Paper Code
  • 7

    SimAD: A Simple Dissimilarity-based Approach for Time Series Anomaly Detection

    Z. Zhong, Z. Yu, X. Xi, Y. Xu, W. Cao, J. Chen, Y. Yang, K. Yang

    IEEE TNNLS · 2025Q1, IF = 9.7 Paper Code
  • 6

    DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series

    Z. Z. Darban, Y. Yang, G. I. Webb, C. C. Aggarwal, Q. Wen, M. Salehi

    IEEE TKDE · 2025Q1, IF = 9.1 Paper Code
  • 5

    A Pipeline Inspection Gauge Positioning Method Based on Distributed Fiber Optic Vibration Sensing

    S. Du, H. Zhang, C. Gong, Y. Yang, X. Jiang, L. Zhou, T. Zhang, Y. Ma, J. Meng, Y. Li

    IEEE Sensors Journal · 2024Q1, IF = 5.0 Link
  • 4

    A Pipeline Intrusion Detection Method Based on Temporal Modeling and Hierarchical Classification in Optical Fiber Sensing

    C. Gong*, Y. Yang*, H. Zhang, J. Meng, Y. Ma, S. Du, Y. Li

    IEEE Sensors Journal · 2024Q1, IF = 5.0 · equal contribution Link
  • 3

    Localizing and Tracking of In-Pipe Inspection Robots Based on Distributed Optical Fiber Sensing

    C. Zhu, Y. Pu, Y. Yang, Z. Lyu, C. Li, Q. Yang

    Advanced Engineering Informatics (AEI) · 2024Q1, IF = 11.5 Link PDF
  • 2

    Pipeline Safety Early Warning by Multi-feature-fusion CNN and LightGBM Analysis of Signals from Distributed Optical Fiber Sensors

    Y. Yang, H. Zhang, Y. Li

    IEEE Trans. on Instrumentation and Measurement · 2021Q1, IF = 7.0 Link PDF
  • 1

    Long-Distance Pipeline Safety Early Warning: A Distributed Optical Fiber Sensing Semi-Supervised Learning Method

    Y. Yang, H. Zhang, Y. Li

    IEEE Sensors Journal · 2021Q1, IF = 5.0 Link PDF

Books 3 entries

Joy-RL book cover

Joy-RL: Reinforcement Learning Practical Tutorial

Joy-RL：强化学习实践教程 · Posts & Telecom Press, 2025

J. Jiang, Q. Wang, Y. Yang

GitHub Repo E-book Code Jingdong
LeeDL-Tutorial book cover

LeeDL-Tutorial

深度学习详解 · Posts & Telecom Press, 2024

Q. Wang, Y. Yang, J. Jiang

★ JD 2024 Annual Best Books (overall Top 50, 京东2024年度好书) · PTP Excellent New Book of 2024 (人民邮电出版社年度影响力新书)

GitHub Repo E-book Douban Dangdang Jingdong
Easy-RL book cover

Easy-RL: Reinforcement Learning Tutorial

Easy-RL：强化学习教程（蘑菇书） · Posts & Telecom Press, 2022

Q. Wang, Y. Yang, J. Jiang

★ PTP Excellent Book of 2022

GitHub Repo Online Version E-book Douban Taobao Dangdang Jingdong

Preprints 5 entries

  • 5

    Diversified Scaling Inference in Time Series Foundation Models

    R. Hua, Z. Liu, K. Zhang, Y. Yang*

    Preprint 2026 ArXiv Code
  • 4

    PyPOTS: A Python Toolkit for Machine Learning on Partially-Observed Time Series

    W. Du, Y. Yang, L. Qian, J. Wang, Q. Wen

    Preprint 2025 ArXiv Website Repo
  • 3

    Achieving Time Series Reasoning Requires Rethinking Model Design, Tasks Formulation, and Evaluation

    Y. Kong*, Y. Yang*, S. Wang, C. Liu, Y. Liang, M. Jin, S. Zohren, D. Pei, Y. Liu, Q. Wen

    Preprint 2025formerly "Position: Empowering Time Series Reasoning with Multimodal LLMs" ArXiv Repo
  • 2

    Intelligent Cross-Organizational Process Mining: A Survey and New Perspectives

    Y. Yang, Z. Wu, Y. Chu, Z. Chen, Z. Xu, Q. Wen

    Preprint 2024 ArXiv
  • 1

    TSI-Bench: Benchmarking Time Series Imputation

    W. Du*, J. Wang*, L. Qian*, Y. Yang*, F. Liu, Z. Wang, Z. Ibrahim, H. Liu, Z. Zhao, Y. Zhou, W. Wang, K. Ding, Y. Liang, B. A. Prakash, Q. Wen

    Preprint 2024 ArXiv Code

Open-Source Projects

Community projects with 37,000+ GitHub stars in total. Star counts update live.

PyPOTS

2,000+ 180+

A machine learning ecosystem for unified time-series analysis. As a core contributor, I help build this open-source toolkit for modeling partially observed multivariate time series; it integrates 50+ SOTA algorithms across imputation, forecasting, classification, clustering, and anomaly detection.

Over 3M PyPI downloads, with users from 200+ top universities and companies. Part of the PyTorch Ecosystem since 2023.

Website GitHub

LeeDL-Tutorial

16,700+ 3,000+

A Chinese deep learning tutorial (深度学习详解), including an e-book and code.

Topped Jingdong's new-AI-book chart for about 30 days. The print edition was named a PTP Excellent New Book of 2024 and one of JD's 2024 Annual Best Books (overall Top 50).

Douban Dangdang Jingdong

Easy-RL

14,500+ 2,200+

A reinforcement learning tutorial (蘑菇书) with an e-book and an online tutorial, plus an online course with Baidu PaddlePaddle AI Studio that attracted 2,000+ learners.

Topped the new-book charts for computer books on Dangdang and AI books on Jingdong within ten days, with related posts drawing 100,000+ reads. The book is held by the National Library of China and the libraries of Tsinghua University, Shanghai Jiao Tong University, Zhejiang University, the Chinese Academy of Sciences, and Merton College, Oxford, among others. The e-book has been downloaded 10,000+ times, and the print edition was selected as a PTP key book and a PTP Excellent Book of Q1 2022.

Douban Taobao Dangdang Jingdong

Academic Trends Analysis

1,850+ 820+

A data-mining tutorial on analyzing academic trends on arXiv, which I led. It includes a video and a competition on the Alibaba Tianchi platform that drew 4,300+ participating teams.

Poster Link 1 Link 2

Ensemble Learning

1,850+ 820+

An ensemble learning tutorial with a case-study video.

Link

Honors & Awards

  • 2026★Chinese Government Award for Outstanding Self-financed Students Abroad — Class A Special Excellence Award (国家优秀自费留学生奖学金·特别优秀奖), China Scholarship Council (Intro)
  • 2026★Most Anticipated Academic Rising Star, QingYuan InnoVibe 2026 (青源InnoVibe 2026——最受瞩目学术新星), Beijing Academy of Artificial Intelligence (BAAI) [Link]
  • 2026Google PhD Fellowship Nominee (nominated by the University of Oxford)
  • 20262025 Influential Author, Epubit, PTPress
  • 2025JEB Outstanding Paper Prize 2025 (Shortlisted), Journal of Experimental Biology, The Company of Biologists
  • 2025Interspeech 2025 Conference Travel Grant
  • 2025Graduate Research Grant, Merton College, University of Oxford
  • 20242024 Excellent New Book (深度学习详解) and Influential Author, Epubit, PTPress; one of JD's 2024 Annual Best Books (overall Top 50)
  • 20232022 Bestselling Book (Easy-RL：强化学习教程) and Influential Author, Epubit, PTPress [Link] [Picture 1] [Picture 2] [Certification] [Trophy]
  • 2022★Clarendon Scholar, University of Oxford
  • 2022★Outstanding Graduate, Beijing
  • 2022Outstanding Master's Thesis, Tsinghua University
  • 2022Outstanding Graduate, Department of Automation, Tsinghua University
  • 2022First-Class Internship Scholarship, SIGS, Tsinghua University (15,000 CNY)
  • 2022PTP Excellent Book Author, Q1 2022 [Picture]
  • 2021★China National Scholarship
  • 2021Datawhale Contributor
  • 2020National Second Prize, 17th National Postgraduate Mathematical Modelling Competition
  • 2020Second-class Scholarship, Tsinghua University
  • 2020Kaggle Competitions Expert, top 1,000 worldwide (0.67%)
  • 2019Outstanding Graduate, Huazhong University of Science and Technology
  • 2018★First Prize (National Champion), 13th National Student Smart Car Competition, Wireless Energy Saving Category
  • 2018First-Class (Grand Prize) Goodix Scholarship (15,000 CNY)
  • 2018National Encouragement Scholarship, Ministry of Education in China
  • 2017First Prize in South China, 12th National Student Smart Car Competition, Optoelectronic Balance Category

Academic Service & Activities

Conference Reviewing & Committees

Reviewer: NeurIPS (2023–2025) · AAAI (2023–2027) · ACL (2025) · KDD (2023–2024) · WWW (2025) · Interspeech (2026) · SLT (2026) · SDM (2024)
Program Committee: 9th–11th SIGKDD Workshop on Mining and Learning from Time Series (MILETS)
Technical Program Committee: IJCNN (2023–2025)

Journal Reviewing 30+ journals

  • IEEE TPAMI
  • IEEE TKDE
  • ACM TKDD
  • IEEE TIFS
  • ACM TOS
  • IEEE TNNLS
  • ACM TOMM
  • ACM TIST
  • IEEE TCYB
  • IEEE TCSVT
  • IEEE TCAS-I
  • IEEE TII
  • IEEE IoT Journal
  • IEEE TITS
  • IEEE TSMC
  • IEEE TBD
  • IEEE SPL
  • IEEE JBHI
  • IEEE/CAA J. Automatica Sinica
  • Information Fusion
  • Pattern Recognition
  • Neural Networks
  • Neurocomputing
  • Knowledge-Based Systems
  • Signal Processing
  • Mechanical Systems and Signal Processing
  • Information Processing & Management
  • Applied Soft Computing
  • Engineering Applications of AI
  • Computer Networks
  • Ecological Informatics
  • Measurement
  • J. of Medical Internet Research

Teaching

  • 2025.02 — Co-leader of the iECDT Deep Learning Course, University of Oxford
  • 2024.04 – 06 — Teaching Assistant, "Machine Learning", Department of Computer Science, University of Oxford
  • 2024.04 – 06 — Teaching Assistant, "Artificial Intelligence", Department of Computer Science, University of Oxford
  • 2020 — Teaching Assistant for Nicholas Lane's "Introduction to Deep Learning" course, University of Cambridge
  • 2020 — Teaching Assistant for Rakesh Kumar's "Artificial Intelligence for Undergraduates" course, UIUC

Community & Leadership

  • 2023.03 – 2024.03 — MCR Social Secretary, Merton College, University of Oxford
  • 2020.06 – Now — Datawhale member (an open-source AI organization), helping data science enthusiasts get involved in the AI community
  • 2019 – 2022 — Member of the Tsinghua University Shenzhen TAP Choir
  • 2019 — Debate chair of the Shenzhen government-sponsored university debate tournament [Picture]
  • 2017 — Top 10 Singer of the School of Artificial Intelligence and Automation, HUST [Link]
  • 2015 – 2019 — Member of the college emcee team; hosted two welcome parties and a graduation gala

Invited Talks & Live Streams