Haiyue Song 宋海越

prof_pic.jpg

Haiyue Song is an LLM engineer at Preferred Networks. Previously, he worked at the National Institute of Information and Communications Technology. He received his Ph.D. in Informatics from Kyoto University in 2024 advised by Prof. Sadao Kurohashi.

His current research focuses on large language models, including agent harness, long-context, reinforcement learning, and continual pre-training. Previously, he worked on machine translation, especially in low-resource, multilingual, and multimodal scenarios.

News

Aug 20, 2026 Three papers accepted to EMNLP 2026 (one Main, two Findings)!
Oct 24, 2025 Four papers accepted to IJCNLP-AACL 2025 (three Main, one System Demonstrations)!
Aug 19, 2025 One paper accepted to EMNLP 2025 Findings!
May 31, 2025 Organizing the English-Indic Language Document Translation Task at WAT 2025.
Mar 31, 2025 Obtained a Grant-in-Aid for Early-Career Scientists!
Jan 31, 2025 Serving as Website Chair for EMNLP 2025.
Jan 19, 2025 Presented a tutorial at COLING 2025.

Education

Kyoto University

Supervised by Prof. Sadao Kurohashi and Prof. Chenhui Chu.

  • Ph.D. in Informatics, October 2020 - March 2024
  • Master in Intelligence Science and Technology, October 2018 - September 2020

Shanghai Jiao Tong University

Supervised by Prof. Li Jiang.

  • Bachelor of Computer Science and Technology, September 2014 - July 2018
  • Minor in Japanese, School of Foreign Languages, February 2015 - July 2018

Nagoya University

  • Exchange student in NUPACE program, October 2017 - February 2018

Work Experience

Preferred Networks

  • Engineer, April 2026 - present

National Institute of Information and Communications Technology (NICT)

  • Technical researcher, July 2023 - March 2026
  • Research internship, October 2019 - June 2023

JSPS

  • Research Fellowship for Young Scientists (DC1), April 2021 - June 2023

Kyoto University

  • Research assistant, November 2020 - March 2021

LINE

  • Internship, machine learning team, February 2019 - March 2019

Selected Publications

  1. EMNLP
    optimer.png
    OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training
    Haiyue Song and Masao Utiyama
    Accepted to EMNLP 2026 Main
  2. IJCNLP-AACL
    formatrl.png
    Structured Document Translation via Format Reinforcement Learning
    IJCNLP-AACL 2025 Main
  3. IWSLT
    iwslt.png
    NICT’s Cascaded and End-To-End Speech Translation Systems using Whisper and IndicTrans2 for the Indic Task
    Raj Dabre and Haiyue Song
    IWSLT 2024
  4. EAMT
    submerge.png
    SubMerge: Merging Equivalent Subword Tokenizations for Subword Regularized Models in Neural Machine Translation
    EAMT 2024
  5. LREC-COLING
    nglueni.png
    NGLUEni: Benchmarking and Adapting Pretrained Language Models for Nguni Languages
    Francois Meyer, Haiyue Song, Abhisek Chakrabarty, Jan Buys, Raj Dabre, and Hideki Tanaka
    LREC-COLING 2024
  6. JNLP
    diverseg.png
    DiverSeg: Leveraging Diverse Segmentations with Cross-granularity Alignment for Neural Machine Translation
    Journal of Natural Language Processing, 2024
  7. TALLIP
    selfseg.png
    SelfSeg: A Self-supervised Sub-word Segmentation Method for Neural Machine Translation
    TALLIP, Aug 2023
  8. AACL
    bertseg.png
    BERTSeg: BERT Based Unsupervised Subword Segmentation for Neural Machine Translation
    AACL-IJCNLP 2022 Main
  9. LREC
    coursera.png
    Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation
    LREC 2020
  10. ICCAD
    iccad.png
    Invocation-driven neural approximate computing with a multiclass-classifier and multiple approximators
    Haiyue Song, Chengwen Xu, Qiang Xu, Zhuoran Song, Naifeng Jing, Xiaoyao Liang, and Li Jiang
    ICCAD 2018

Academic Service

  • Website Chair: EMNLP 2025.
  • Area Chair: ARR 2025, ARR 2026 March.
  • Workshop Co-organizer: WAT 2024, and the English-Indic Language Document Translation Task at WAT 2025.
  • Mentor: AACL 2020 Student Research Workshop.
  • Award Selection Committee: ANLP (in Japan) 2026.
  • Candidate for KAKENHI Review Committee Member 2026.
  • Reviewer: JNLP 2026, EAMT 2026, TALLIP 2026, TASLP 2026, IEICE 2026, ARR 2026 May, ARR 2026 January, LREC 2026, IJCNLP-AACL 2025, WAT 2025, EMNLP 2025, ACL 2025, COLING 2025, NLPCC 2024, TASLP 2024, AMTA 2024, LREC-COLING 2024, four rounds of ARR 2024, TALLIP 2024, TASLP 2023, TALLIP 2023, ARR 2023, APSIPA ASC 2023, EMNLP 2023, ACL 2023, EMNLP 2022, EMNLP 2021, EMNLP 2020, IJCNLP 2020, WAT 2020, etc.

Grants

  1. KAKENHI
    Improving Large Language Models for Low-Resource Languages with Diverse Writing Systems
    Haiyue Song
    2025
    Grant-in-Aid for Early-Career Scientists(若手研究), 2025 to 2026, KAKENHI 25K21290.
  2. KAKENHI
    Multilingual Corpus Construction and Domain Adaptation for Low-Resource Machine Translation
    Haiyue Song
    2021
    JSPS Research Fellowship for Young Scientists (DC1), 2021 to 2023, KAKENHI 22KJ1724.

Others

  1. Talk
    Presentation at CJNLP 2024
    Haiyue Song
    2024
  2. Talk
    Presentation at the 14th Input Method Workshop (IM 2022)
    Haiyue Song
    2022
    第14回入力メソッドワークショップ
  3. Talk
    Presentation at the Kyoto University Symposium of the Department of Intelligence Science and Technology (AY2022)
    Haiyue Song
    2022
    2022年度 京都大学 情報学研究科 知能情報学専攻 シンポジウム
  4. Talk
    Lecture at 知能情報学演習, Kyoto University
    Haiyue Song
    2022
  1. Patent
    One patent application in progress

Hobbies

Competitive Programming

  • Silver medal at the National Olympiad in Informatics (NOI) 2013, Chengdu, China.
  • Bronze medal at the Asia-Pacific Informatics Olympiad (APIO) 2013.
  • AtCoder profile.

Japanese

  • Passed the Japanese Language Proficiency Test N1 (the highest level) in 2017.

Sports