黄锴宇
博士 、助理研究员
基本信息
| 办公电话： | 电子邮件： kyhuang@bjtu.edu.cn |
| 通讯地址：北京交通大学计算机与信息技术学院 | 邮编：100044 |
个人介绍
北京交通大学计算机科学与技术学院讲师，北京交通大学青英人才计划，在国际顶级会议和期刊发表论文60余篇，主要研究兴趣为自然语言处理、预训练模型和科学智能等。曾任清华大学智能产业研究院(AIR)博士后，从事预训练大模型、机器翻译和持续学习等方向进行技术研究和产品研发。曾获ACL杰出论文奖，EMNLP领域亮点论文奖，优秀博士论文奖。在人工智能、信息检索和复合材料科学等领域具备丰富的交叉学科知识和研究经历。
长期招收访问实习生（科研系列），欢迎感兴趣的同学与我联系。
研究方向包括但不仅限于：Multilingual AI, Trustworthy AI, Geospatial AI
我们的目标是做一流的科学研究，发表高水平论文，扩展认知边界，推动前沿技术落地和产业进步。
我们有丰富的产业界经验，实现多项AI算法的产品转化，熟悉AI产品落地应用化流程。
无论你毕业后的目标是学术界还是工业界，相信在这里都会有所收获。
ps: 我们会优先从有合作经历、互相了解的学生中招收研究生，如果可能，尽量提前来实习。
访问实习生要求了解一定的深度学习算法和具备编程基础，能够自主进行文献阅读和算法实现。
团队与清华大学，蒙特利尔大学，爱丁堡大学，东京大学等国内外高校保持深度交流，与华为，百度，腾讯等企业保持深度合作。
可为优秀访问实习生向学界和产业界提供推荐和联合培养等机会。
论文/期刊
完整论文列表参考谷歌学术 https://scholar.google.com/citations?user=qAp-hS4AAAAJ
个人主页 https://kaiyuhwang.github.io/
Multilingual AI
- Rui Qi, Zhibo Man, Yufeng Chen, Fengran Mo, Jinan Xu, Kaiyu Huang. SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Models. In Findings of EMNLP 2025.
- Chao Huang, Fengran Mo, Yufeng Chen, Changhao Guan, Zhenrui Yue, Xinyu Wang, Jinan Xu, Kaiyu Huang. Boosting Data Utilization for Multilingual Dense Retrieval. In Proceedings of EMNLP 2025.
- 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).
- 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.
- Xue Zhang, Yunlong Liang, Fandong Meng, Songming Zhang, Kaiyu Huang, Yufeng Chen, Jinan Xu, Jie Zhou. Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning. In Proceedings of ACL 2026.
- Rui Qi, Fengran Mo, Yufeng Chen, Xue Zhang, Shuo Wang, Hongliang Li, Jinan Xu, Meng Jiang, Jian-Yun Nie, Kaiyu Huang. Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation. In Findings of ACL 2026.
- Junpeng Liu, Jiuyi Li, Kaiyu Huang, Bo Jin, Degen Huang, Hui Xiong. SiLP: Enhancing Non-Dominant Language Capabilities with a Selective Bidirectional Language Projection Framework. In Proceedings of ACL 2026.
- 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.
- Chao Huang, Yufeng Chen, Changhao Guan, Guang Yang, Dongze Chen, Kaiyu Huang. Disentangled Contrastive Learning for Zero-Shot Multilingual Dense Retrieval. In arXiv:2608.02189.
- 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.
Efficient Adaptation
- Yulong Mao, Kaiyu Huang, Changhao Guan, Ganglin Bao, Fengran Mo, Jinan Xu. DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution. In Proceedings of ACL 2024.
- Guang Yang, Changhao Guan, Chao Huang, Yufeng Chen, Kaiyu Huang. Adaptive Utilization of Low-Rank Adaptation via Conditioned Gating. In Proceedings of ICML 2026.
Geospatial AI
- 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.
- 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.
Trustworthy AI
- Hongliang Li, Jinan Xu, Gengping Cui, Changhao Guan, Fengran Mo, Kaiyu Huang. Multilingual Collaborative Defense for Large Language Models. In Findings of EMNLP 2025.
- 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)
- 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.
Machine Translation
- Kaiyu Huang, Peng Li, Jin Ma, Yang Liu. Entropy-based Vocabulary Substitution for Incremental Learning in Multilingual Neural Machine Translation. In Proceedings of EMNLP 2022.
- Junpeng Liu, Kaiyu Huang, Jiuyi Li, Huan Liu, Jinsong Su, Degen Huang. Adaptive Token-level Cross-lingual Feature Mixing for Multilingual Neural Machine Translation. In Proceedings of EMNLP 2022.
- Kaiyu Huang, Peng Li, Jin Ma, Ting Yao, Yang Liu. Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation. In Proceedings of ACL 2023. (Outstanding Paper Award)
- Junpeng Liu, Kaiyu Huang, Hao Yu, Jiuyi Li, Jinsong Su, Degen Huang. Continual Learning for Multilingual Neural Machine Translation via Dual Importance-based Model Division. In Proceedings of EMNLP 2023.
- Kaiyu Huang, Peng Li, Junpeng Liu, Maosong Sun, Yang Liu. Learn and Consolidate: Continual Adaptation for Zero-Shot and Multilingual Neural Machine Translation. In Proceedings of EMNLP 2023.
- Hao Yu, Kaiyu Huang, Anqi Zhao, Junpeng Liu, Degen Huang. Context-Aware Non-Autoregressive Document-Level Translation with Sentence-Aligned Connectionist Temporal Classification. In Proceedings of COLING 2024.
- Zhibo Man, Kaiyu Huang, Yujie Zhang, Yuanmeng Chen, Yufeng Chen, Jinan Xu. ICL: Iterative Continual Learning for Multi-domain Neural Machine Translation. In Findings of EMNLP 2024.
- Hao Yu, Degen Huang, Kaiyu Huang. Hierarchical Local-Global Transformer With Dynamic Positional Encoding for Document-Level Machine Translation. IEEE Transactions on Audio, Speech and Language Processing 2025(33).
- Hao Zong, Cong Hu Yuan, Chao Bei, Wentao Chen, Huan Liu, Kaiyu Huang, Degen Huang. One Pair Suffices: Unlocking Universal Zero-Shot Translation via Cross-Architecture Alignment. In Proceedings of ACL 2026.
科研项目
- 基本科研业务费研究生创新项目: 多模态大模型的主动式安全内容生成研究, 2026-2028
- 基本科研业务费研究生创新项目: 知识驱动的多语言大模型推理研究, 2026-2028
- 自然科学横向项目: 面向内容恶意识别的大模型与Agent应用研究, 2026-2027
- 自然科学横向项目: 面向知识密集型文档库的检索增强技术研究, 2026-2027
- 自然科学横向项目: 中知慧海知识产权大数据系统智能化其AI辅助撰写权利要求书功能委托开发, 2025-2026
- 自然科学横向项目: 多语言机器翻译系统, 2025-2028
- 自然科学横向项目: 面向短视频评论的负面价值观内容识别, 2025-2025
- 国家自然科学基金"青年基金": 突破语言隔阂的多语言大模型关键技术研究, 2025-2027
- 红果园省部级"企事业"（新）: 时间约束下资源调度决策传统算法研究、训练环境构建及测试评估, 2024-2027
- 国家级平台专项: 铁路大模型基础数据平台构建关键技术研究, 2024-2026
- 自然科学类人才基金项目: 面向多语言神经机器翻译的增量学习研究, 2024-2027
获奖与荣誉
- 2023年，北京交通大学青英人才计划
- 2023年，ACL 2023杰出论文奖（第一作者）
- 2025年，EMNLP 2025领域亮点论文奖（通讯作者）
- 2025年，CCMT 2025亮点英文论文奖（通讯作者）
社会兼职
- 中国中文信息学会青年工作委员会：专委（2024-至今）
- 中国中文信息学会计算语言学委员会：专委（2026-至今）
-
中国计算机学会自然语言处理委员会：执委（2026-至今）