avatar

Xinyu Wang

xnyuwang@gmail.com


Welcome to my personal space!

I recently completed my PhD from the Department of Computer Science, University of Warwick, where I was also a visiting PhD student at the Department of Informatics, King’s College London. Before the PhD adventure, I studied at the Beijing University of Posts and Telecommunications.

I also worked as an Applied Scientist Intern at Amazon AWS focusing on Large Language Models, as an Algorithm Engineer at the XiaoAi Group of Xiaomi, and as a Research Intern at IBM Research.

I currently focus on LLMs, especially Reasoning, Multi-Agent, and Efficiency. In the past, I have worked on Long-Context Understanding, Dialogue System, and Multi-modality.

Selected Publications

  1. NeurIPS'25
    Block-Diagonal LoRA for Eliminating Communication Overhead in Tensor Parallel LoRA Serving
    Xinyu Wang, Jonas M. Kübler, Kailash Budhathoki, Yida Wang, Matthäus Kleindessner
    NeurIPS'25 | The Thirty-ninth Annual Conference on Neural Information Processing Systems
    Page Slides BibTex

  2. ACL'25
    PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA
    Xinyu Wang, Yanzheng Xiang, Lin Gui, Yulan He
    ACL'25 | Findings of the Association for Computational Linguistics: ACL 2025
    Page Slides BibTex

  3. ACL'24
    Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond
    Xinyu Wang, Hainiu Xu, Lin Gui, Yulan He
    ACL'24 | Findings of the Association for Computational Linguistics: ACL 2024
    Page Slides BibTex

  4. ACL'23
    Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization
    Xinyu Wang, Lin Gui, Yulan He
    ACL'23 | Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 2023.
    Page Slides BibTex

  5. EMNLP'23
    A Scalable Framework for Table of Contents Extraction from Complex ESG Annual Reports
    Xinyu Wang, Lin Gui, Yulan He
    EMNLP'23 | Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023.
    Page Slides BibTex

Full List of Publications

  1. EMNLP'25
    NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning
    Wei Liu, Siya Qi, Xinyu Wang, Chen Qian, Yali Du, Yulan He
    EMNLP'25 | Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025.
    Page BibTex

  2. ACL'24
    Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning
    Hanqi Yan, Qinglin Zhu, Xinyu Wang, Lin Gui, Yulan He
    ACL'24 | Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, 2024.
    Page BibTex

  3. COLING'24-FinNLP-KDF-ECONLP
    Topic Taxonomy Construction from ESG Reports
    Saif Majdi AlNajjar, Xinyu Wang, Yulan He
    COLING'24-FinNLP-KDF-ECONLP | Proceedings of the Joint Workshop of the 7th Financial Technology and Natural Language Processing, the 5th Knowledge Discovery from Unstructured Data in Financial Services, and the 4th Workshop on Economics and Natural Language Processing @ LREC-COLING 2024
    Page BibTex

  4. EMNLP'20-NLPBT
    Building a Bridge: A Method for Image-Text Sarcasm Detection Without Pretraining on Image-Text Data
    Xinyu Wang, Xiaowen Sun, Tan Yang, Hongbo Wang
    EMNLP'20-NLPBT | Proceedings of the First International Workshop on Natural Language Processing Beyond Text, 2020.
    Page BibTex

  5. EMNLP'20-DeeLIO
    Correcting the Misuse: A Method for the Chinese Idiom Cloze Test
    Xinyu Wang, Hongsheng Zhao, Tan Yang, Hongbo Wang
    EMNLP'20-DeeLIO | Proceedings of Deep Learning Inside Out: The First Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, 2020.
    Page BibTex

  6. IEEE Access
    BSENet: A Data-Driven Spatio-Temporal Representation Learning for Base Station Embedding
    Xinyu Wang, Tan Yang, Yidong Cui, Yuehui Jin, Hongbo Wang
    IEEE Access, 2020.
    Page BibTex

  7. Book
    [Book] An Introduction and Hands-On Guide to Natural Language Processing with PyTorch
    Xiaowen Sun, Xinyu Wang, Tan Yang
    Posts and Telecommunications Press, 2022.
    Page


Powered by Jekyll and Minimal Light theme.