% FloatAI publications. The homepage list is rendered from this file.
%
% Standard BibTeX fields are used for citation. Three extra fields control the
% homepage and are ignored by BibTeX:
%   category  topic label, e.g. "Pretraining"
%   venue     short venue shown in the list, e.g. "EMNLP 2025"
%   page      project page on this site; the row links here instead of url
%
% The list is sorted by year and month, newest first. Entries from the same
% month keep their order in this file.

@misc{chai2026repeated,
  category      = {Pretraining},
  venue         = {arXiv preprint},
  page          = {/research/repeated-tokens/},
  title         = {What Is a Repeated Token Worth? The Scaling Geometry of
                   Multi-Epoch Pretraining},
  author        = {Yekun Chai and Haoyi Xiong},
  year          = {2026},
  month         = oct,
  eprint        = {2610.05591},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2610.05591}
}

@misc{chai2026xiangqibench,
  category      = {Agents},
  venue         = {arXiv preprint},
  page          = {/research/xiangqibench/},
  title         = {Finding the Move Is Not Winning the Game:
                   {XiangqiBench} for Closed-Loop Evaluation of {LLM} Agents},
  author        = {Yekun Chai and Qiwei Peng and Haoyi Xiong},
  year          = {2026},
  month         = oct,
  eprint        = {2610.02425},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2610.02425}
}

@inproceedings{peng-etal-2025-understanding,
    category = "Tokenization",
    venue = "EMNLP 2025",
    title = "Understanding Subword Compositionality of Large Language Models",
    author = "Peng, Qiwei  and
      Chai, Yekun  and
      S{\o}gaard, Anders",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.emnlp-main.1146/",
    doi = "10.18653/v1/2025.emnlp-main.1146",
    pages = "22524--22535",
    ISBN = "979-8-89176-332-6"
}

@inproceedings{peng-etal-2025-debiasing,
    category = "Multilingual",
    venue = "EMNLP 2025",
    title = "Debiasing Multilingual {LLM}s in Cross-lingual Latent Space",
    author = "Peng, Qiwei  and
      Hu, Guimin  and
      Chai, Yekun  and
      S{\o}gaard, Anders",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.emnlp-main.1149/",
    doi = "10.18653/v1/2025.emnlp-main.1149",
    pages = "22582--22593",
    ISBN = "979-8-89176-332-6"
}

@inproceedings{yang-chai-2025-codemixbench,
    category = "Multilingual",
    venue = "EMNLP 2025",
    title = "{C}ode{M}ix{B}ench: Evaluating Code-Mixing Capabilities of {LLM}s Across 18 Languages",
    author = "Yang, Yilun  and
      Chai, Yekun",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.emnlp-main.109/",
    doi = "10.18653/v1/2025.emnlp-main.109",
    pages = "2139--2169",
    ISBN = "979-8-89176-332-6"
}

@inproceedings{yu-chai-2025-evolkv,
    category = "Efficiency",
    venue = "Findings of EMNLP 2025",
    title = "{E}vol{KV}: Evolutionary {KV} Cache Compression for {LLM} Inference",
    author = "Yu, Bohan  and
      Chai, Yekun",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-emnlp.88/",
    doi = "10.18653/v1/2025.findings-emnlp.88",
    pages = "1673--1689",
    ISBN = "979-8-89176-335-7"
}

@inproceedings{nakamura-etal-2025-aurora,
    category = "Pretraining",
    venue = "COLING 2025 (Industry)",
    title = "Aurora-{M}: Open Source Continual Pre-training for Multilingual Language and Code",
    author = "Nakamura, Taishi  and
      Mishra, Mayank  and
      Tedeschi, Simone  and
      Chai, Yekun  and
      Stillerman, Jason T.  and
      Friedrich, Felix  and
      Yadav, Prateek  and
      Laud, Tanmay  and
      Chien, Vu Minh  and
      Zhuo, Terry Yue  and
      Misra, Diganta  and
      Bogin, Ben  and
      Vu, Xuan-Son  and
      Karpinska, Marzena  and
      Dantuluri, Arnav Varma  and
      Kusa, Wojciech  and
      Furlanello, Tommaso  and
      Yokota, Rio  and
      Muennighoff, Niklas  and
      Pai, Suhas  and
      Adewumi, Tosin  and
      Laippala, Veronika  and
      Yao, Xiaozhe  and
      Junior, Adalberto Barbosa  and
      Drozd, Aleksandr  and
      Clive, Jordan  and
      Gupta, Kshitij  and
      Chen, Liangyu  and
      Sun, Qi  and
      Tsui, Ken  and
      Moustafa-Fahmy, Nour  and
      Monti, Nicolo  and
      Dang, Tai  and
      Luo, Ziyang  and
      Bui, Tien-Tung  and
      Navigli, Roberto  and
      Mehta, Virendra  and
      Blumberg, Matthew  and
      May, Victor  and
      Nguyen, Hiep  and
      Pyysalo, Sampo",
    editor = "Rambow, Owen  and
      Wanner, Leo  and
      Apidianaki, Marianna  and
      Al-Khalifa, Hend  and
      Eugenio, Barbara Di  and
      Schockaert, Steven  and
      Darwish, Kareem  and
      Agarwal, Apoorv",
    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics: Industry Track",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.coling-industry.56/",
    pages = "656--678"
}

@inproceedings{peng-sogaard-2024-concept,
    category = "Multilingual",
    venue = "EMNLP 2024",
    title = "Concept Space Alignment in Multilingual {LLM}s",
    author = "Peng, Qiwei  and
      S{\o}gaard, Anders",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.emnlp-main.315/",
    doi = "10.18653/v1/2024.emnlp-main.315",
    pages = "5511--5526"
}

@inproceedings{chai-etal-2024-tokenization,
    category = "Tokenization",
    venue = "Findings of EMNLP 2024",
    page = "/research/tkeval/",
    title = "Tokenization Falling Short: On Subword Robustness in Large Language Models",
    author = "Chai, Yekun  and
      Fang, Yewei  and
      Peng, Qiwei  and
      Li, Xuhong",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.86/",
    doi = "10.18653/v1/2024.findings-emnlp.86",
    pages = "1582--1599"
}

@inproceedings{li2024gilot,
  category  = {Interpretability},
  venue     = {ICML 2024},
  title     = {{GiLOT}: Interpreting Generative Language Models via Optimal Transport},
  author    = {Li, Xuhong and Chen, Jiamin and Chai, Yekun and Xiong, Haoyi},
  booktitle = {Proceedings of the 41st International Conference on Machine Learning},
  series    = {Proceedings of Machine Learning Research},
  volume    = {235},
  pages     = {27515--27530},
  year      = {2024},
  month     = jul,
  publisher = {PMLR},
  url       = {https://proceedings.mlr.press/v235/li24i.html}
}

@inproceedings{peng-etal-2024-humaneval,
    category = "Multilingual",
    venue = "LREC-COLING 2024",
    page = "/research/humaneval-xl/",
    title = "{H}uman{E}val-{XL}: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization",
    author = "Peng, Qiwei  and
      Chai, Yekun  and
      Li, Xuhong",
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://aclanthology.org/2024.lrec-main.735/",
    pages = "8383--8394"
}