Kaiyu Huang

I am a research assistant professor at the School of Computer Science and Technology of Beijing Jiaotong University, forming the Language Intelligence Explorer (LIE) Lab. I received ACL 2023 Outstanding Paper Award and EMNLP 2025 SAC Highlight Award. I was a postdoc at the Institute for AI Industry Research (AIR) of Tsinghua University (09.2023), working with Prof. Yang Liu. I obtained a Ph.D. degree in the School of Computer Science at Dalian University of Technology (09.2021), advised by Prof. Degen Huang.

Email: kyhuang@bjtu.edu.cn
Office: Room 423, Building of Civil Engineering, Beijing Jiaotong University
Profiles: Google Scholar · ORCID

Research Interests

LIE favors the following research perspectives with three talking groups, including Multilingual AI (X-Group), Trustworthy AI (Safety-Group) and Geospatial AI (Geo-Group).

Selected Publications

A short selection of representative work. For a complete list, see my Google Scholar profile.

Multilingual AI

  • Rui Qi, Yufeng Chen, Yunlong Liang, Chuan Meng, Sijin Lu, Ge Shi, Jinan Xu, Fandong Meng, Kaiyu Huang. Rewrite What Matters: Adaptive Multilingual Query Rewriting for Reasoning via Agentic Reinforcement Learning. In arXiv:2610.04899.
  • Hongliang Li, Yijin Liu, Zhiwei Zhang, Zihe Liu, Xinyue Lou, Jinan Xu, Fandong Meng, Kaiyu Huang. PolyWorkBench: Benchmarking Multilingual Long-Horizon LLM Agents. In arXiv:2607.06008.
  • Rui Qi, Fengran Mo, Sijin Lu, Yufeng Chen, Jian-Yun Nie, Kaiyu Huang. CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generation. In Proceedings of SIGIR 2026.
  • Kaiyu Huang, Fengran Mo, Xinyu Zhang, Hongliang Li, You Li, Yuanchi Zhang, Weijian Yi, Yulong Mao, Jinchen Liu, Yuzhuang Xu, Jinan Xu, Jian-Yun Nie, Yang Liu. A survey on large language models with multilingualism: recent advances and new frontiers. Artificial Intelligence Review 2026(59).

Trustworthy AI

  • Xinyue Lou, Jinan Xu, Jingyi Yin, Xiaolong Wang, Zhaolu Kang, Yixuan Wang, Xiangyu Shi, Fengran Mo, Su Yao, Kaiyu Huang. When Helpers Become Hazards: A Benchmark for Analyzing Multimodal LLM-Powered Safety in Daily Life. In Findings of ACL 2026.
  • Xinyue Lou, You Li, Jinan Xu, Xiangyu Shi, Chi Chen, Kaiyu Huang. Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model. In Proceedings of EMNLP 2025 (SAC Highlight Award).
  • Hongliang Li, Jinan Xu, Gengping Cui, Changhao Guan, Fengran Mo, Kaiyu Huang. Multilingual Collaborative Defense for Large Language Models. In Findings of EMNLP 2025.

Geospatial AI

  • Yongan Yu, Xianda Du, Qingchen Hu, Jiahao Liang, Jingwei Ni, Dan Qiang, Kaiyu Huang, Grant Mckenzie, Renée Sieber, Fengran Mo. WeatherArchive: A Benchmark for Retrieval-Augmented Reasoning over Historical Weather Archives. In Proceedings of SIGIR 2026.
  • Long Yuan, Fengran Mo, Kaiyu Huang, Wenjie Wang, Wangyuxuan Zhai, Xiaoyu Zhu, You Li, Jinan Xu, Jian-Yun Nie. OmniGeo: Towards a Multimodal Large Language Models for Geospatial Artificial Intelligence. In arXiv:2503.16326.