An Wang

An Wang

Ph.D. Student in Computer Science

Introduction

Hello, I am An Wang (王安), a final-year Ph.D. student at Tokyo Institute of Technology. My research interest includes model architecture and training strategy of large language models (LLMs).

Educations

  • 2015 - 2019, Undergraduate student in the School of Mechatronic Engineering and Automation, Shanghai University
  • 2020 - 2022, Master student in the Department of Computer Science, Tokyo Institute of Technology, advised by Prof. Yokota Haruo.
  • 2022 - 2025, doctoral student in the Department of Computer Science, Tokyo Institute of Technology, advised by Prof. Naoaki Okazaki.

Internships

  • 2019.8 - 2019.10, Nature Language Understanding Team, Intsig, Shanghai, China
  • 2023.10 - 2024.2, Human-centric Team, NEC Laboratories Europe, Heidelberg, Germany
  • 2024.5 - Now, LLM Pretraining Team (Qingyun Project), Hunyuan Team, TEG, Tencent, Beijing, China

PrePrint

  1. An Wang*, Xingwu Sun*, Ruobing Xie, Shuaipeng Li, Jiaqi Zhu, Zhen Yang, Pinxue Zhao, JN Han, Zhanhui Kang, Di Wang, Naoaki Okazaki, Cheng-zhong Xu. HMoE: Heterogeneous Mixture of Experts for Language Modeling. 2024. arXiv.
  2. Xingwu Sun, Shuaipeng Li, Ruobing Xie, Weidong Han, Kan Wu, Zhen Yang, Yixing Li, An Wang, Shuai Li, Jinbao Xue, Yu Cheng, Yangyu Tao, Zhanhui Kang, Chengzhong Xu, Di Wang, Jie Jiang. Scaling Laws for Floating–Point Quantization Training. 2025. arXiv.
  3. Zhen Yang, J.N.Han, Kan Wu, Ruobing Xie, An Wang, Xingwu Sun, Zhanhui Kang. Lossless KV Cache Compression to 2%. 2024. arXiv.
  4. An Wang, Ao Liu, Hieu Hanh Le, Haruo Yokota. Towards Effective Multi-Task Interaction for Entity-Relation Extraction: A Unified Framework with Selection Recurrent Network. 2022. arXiv.

International Conferences

  1. An Wang, Junfeng Jiang, Youmi Ma, Ao Liu, and Naoaki Okazaki. 2023. Generative Data Augmentation for Aspect Sentiment Quad Prediction. In Proceedings of the 12th Joint Conference on Lexical and Computational Semantics. Association for Computational Linguistics. *SEM@ACL 2023. Toronto, Canada. 13 pages (double columns)
  2. Youmi Ma, An Wang, and Naoaki Okazaki. Building a Japanese Document-Level Relation Extraction Dataset Assisted by Cross-Lingual Transfer. LREC-COLING 2024, 13 pages (double columns).
  3. Youmi Ma, An Wang, Naoaki Okazaki. 2023 DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction, EACL 2023, 13 pages (double columns).
  4. Ao Liu, An Wang and Naoaki Okazaki. 2022. Semi-Supervised Formality Style Transfer with Consistency Training. ACL 2022, 13 pages (double columns).
  5. An Wang*, Junfeng Jiang*, and Akiko Aizawa. 2021. Attention-based Relational Graph Convolutional Network for Target-Oriented Opinion Words Extraction. EACL 2021, 12 pages (double columns)
  6. An Wang, Hieu Hanh Le, Ryosuke Matsuo, Tomoyoshi Yamazaki, Kenji Araki, Haruo Yokota. 2022. MERJ: Medical Entity-Relation Extraction System for Japanese Clinical Texts. DEIM 2022, 8 pages (double columns)

Journal

  1. An Wang, Huidong Jiang, Youmi Ma, Junfeng Jiang, Ao Liu, Naoaki Okazaki. 2025. Improving Implicit Sentiments Analysis via Explanations of Multiple Perspectives. IEEE ACCESS 2025.
  2. An Wang, Huidong Jiang, Youmi Ma, Junfeng Jiang, Ao Liu, Naoaki Okazaki. 2024. Abisa-Ex: Understanding Implicit Sentiments by Explanations. Journal of Nature Language Processing, 2024 Volume 31 Issue 4 1523-1544, December 2024.
  3. An Wang, Junfeng Jiang, Youmi Ma, Ao Liu, and Naoaki Okazaki. Generative Data Augmentation for Aspect Sentiment Quad Prediction. Journal of Natural Language Processing, 31(4):to appear, December 2024.
  4. Youmi Ma, An Wang, and 岡崎 直観. 文書レベル関係抽出における根拠認識の統合. 自然言語処理, 31(1):105–133, March 2024.

Honors and Awards

  1. Excellence Award, the Association for Natural Language Processing. 2025
  2. Best paper Award in the 29th Annual Meeting of The Association for Natural Language Processing. 2023
  3. Advanced Human Resource Development Fellowship for Doctoral Students, Tokyo Institute of Technology, 2022-2023
  4. Spring Scholarship for Doctoral Students, Tokyo Institute of Technology, 2023-2024