Publications

1. ICLR

   A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models

   Lixin Xiu, Xufang Luo, and Hideki Nakayama

   In 14th International Conference on Learning Representations, 2026

   Bib HTML Website

   @inproceedings{xiu2026information,
     title = {A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models},
     author = {Xiu, Lixin and Luo, Xufang and Nakayama, Hideki},
     booktitle = {14th International Conference on Learning Representations},
     year = {2026},
   }

2. ICML Oral

   Bottleneck-Minimal Indexing for Generative Document Retrieval

   Xin Du^*, Lixin Xiu^*, and Kumiko Tanaka-Ishii

   * Equal contribution (co-first authors).

   In 41st International Conference on Machine Learning (Oral), 2024

   arXiv Bib PDF

   @inproceedings{du2024bottleneck,
     title = {Bottleneck-Minimal Indexing for Generative Document Retrieval},
     author = {Du, Xin and Xiu, Lixin and Tanaka-Ishii, Kumiko},
     booktitle = {41st International Conference on Machine Learning},
     series = {Proceedings of Machine Learning Research},
     volume = {235},
     pages = {11888--11904},
     year = {2024},
   }

2026

1. EMNLP Main

   MangaFlow: An End-to-End Agentic Framework for Controllable Story to Manga Generation

   Muyao Wang, Zeke Xie, Yanhao Chen, Lixin Xiu, and Hideki Nakayama

   In 31st Conference on Empirical Methods in Natural Language Processing (Main), 2026

   Not yet publicly available.
2. EMNLP Findings

   Sustaining Cross-Modal Dependency for Generalizable Vision-Language Model Tuning

   Chenhao Ding, Jizhou Han, SongLin Dong, Xinyuan Gao, Qiang Wang, Lixin Xiu, Wei Ke, Yihong Gong, and Hideki Nakayama

   In 31st Conference on Empirical Methods in Natural Language Processing (Findings), 2026

   Not yet publicly available.
3. ICLR

   A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models

   Lixin Xiu, Xufang Luo, and Hideki Nakayama

   In 14th International Conference on Learning Representations, 2026

   Bib HTML Website

   @inproceedings{xiu2026information,
     title = {A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models},
     author = {Xiu, Lixin and Luo, Xufang and Nakayama, Hideki},
     booktitle = {14th International Conference on Learning Representations},
     year = {2026},
   }

2024

1. ICML Oral

   Bottleneck-Minimal Indexing for Generative Document Retrieval

   Xin Du^*, Lixin Xiu^*, and Kumiko Tanaka-Ishii

   * Equal contribution (co-first authors).

   In 41st International Conference on Machine Learning (Oral), 2024

   arXiv Bib PDF

   @inproceedings{du2024bottleneck,
     title = {Bottleneck-Minimal Indexing for Generative Document Retrieval},
     author = {Du, Xin and Xiu, Lixin and Tanaka-Ishii, Kumiko},
     booktitle = {41st International Conference on Machine Learning},
     series = {Proceedings of Machine Learning Research},
     volume = {235},
     pages = {11888--11904},
     year = {2024},
   }