LI Kai李锴

Education教育背景

• 2024 – Present

  Ph.D. Candidate in Data Science博士研究生，数据科学

  City University of Hong Kong (CityU) · School of Data Science香港城市大学（CityU）· 数据科学学院

  • Supervised by Prof. Xiangyu Zhao, Applied Machine Learning Lab (AML).导师：赵翔宇 教授，应用机器学习实验室（AML）。
  • Research on vision-language models and 3D scene understanding.研究方向：视觉语言大模型与三维场景理解。
• 2021 – Present

  Ph.D. Candidate (direct entry), Signal and Information Processing博士研究生（本科直博），信号与信息处理

  University of Chinese Academy of Sciences (UCAS) · Aerospace Information Research Institute中国科学院大学（UCAS）· 空天信息创新研究院

  • Supervised by Prof. Zhongming Zhao and Prof. Yu Meng.导师：赵忠明 教授、孟瑜 教授。
  • Research on building extraction from off-nadir remote sensing imagery.研究方向：偏移摄影视角下的遥感建筑物提取。
• Until 2021

  B.Eng. in Space Information and Digital Technology工学学士，空间信息与数字技术

  University of Electronic Science and Technology of China (UESTC)电子科技大学（UESTC）

  • Ranked 2nd in the major; recommended for direct PhD admission to UCAS.专业排名第 2；获推荐免试直接攻读博士学位（直博）。

Experience研究与实习经历

• 2025.10 – Present

  Research Intern, Omni Research Team研究实习生，Omni 研究团队

  Tencent腾讯

  • Memory mechanisms for video world models — current focus.视频世界模型（Video World Model）的记忆机制研究 —— 当前重心。
  • Reinforcement learning for sparse-view-consistent 3D indoor scene reconstruction; Scenix.基于强化学习的稀疏视角一致性三维室内场景重建；Scenix。
  • Second collaboration with the team.第二次加入该团队。
• 2021 – Present

  Research Assistant, Off-Nadir Remote Sensing Group研究助理，偏移摄影遥感方向

  Aerospace Information Research Institute, Chinese Academy of Sciences中国科学院空天信息创新研究院

  • Built the Offset Token research line: OBM, PolyFootNet, DragOSM, ObliCity/DragRoof, LODEOT.构建偏移量词元研究主线：OBM、PolyFootNet、DragOSM、ObliCity/DragRoof、LODEOT。
• 2021.05 – 2021.09

  Computer Vision Algorithm Intern计算机视觉算法实习生

  Tencent腾讯

  • Surveyed 3D object detection and 3D reconstruction algorithms.调研 3D 目标检测与 3D 重建相关算法。

Mentorship研究生指导

• Jiajun ZhangJiajun Zhang

  M.Sc., City University of Hong Kong · co-mentored with Prof. Xiangyu Zhao香港城市大学硕士研究生 · 与赵翔宇教授联合指导

  • Next position: Ph.D. student at Peking University.下一站：北京大学博士生。
  • Google Scholar profileGoogle Scholar 主页

• Zigan ZhouZigan Zhou

  M.Sc., City University of Hong Kong · co-mentored with Prof. Xiangyu Zhao香港城市大学硕士研究生 · 与赵翔宇教授联合指导

  • Interned at the Chinese Academy of Sciences (CAS).曾于中国科学院实习。

• Weizhi ChenWeizhi Chen

  University of Chinese Academy of Sciences (AIRCAS) · co-mentored with Prof. Jingbo Chen中国科学院大学（空天信息创新研究院）· 与陈静波教授联合指导

  • Published two papers in IEEE JSTARS on CLIP-based remote sensing image-text alignment.以 CLIP 图文对齐为研究方向，发表两篇 IEEE JSTARS 论文。
  • Now an LLM Algorithm Researcher at Zhonggong Education.现任中公教育大模型算法研究员。

Teaching教学经历

• Teaching Assistant, Optimization Methods助教，最优化方法

  Prof. Zhenjiang Zhao · University of Chinese Academy of Sciences赵振江 教授 · 中国科学院大学

• Teaching Assistant, Academic English助教，学术英语

  Prof. James · University of Chinese Academy of SciencesJames 教授 · 中国科学院大学

Publications发表论文

• Prompt-Driven Building Footprint Extraction in Aerial Images with Offset-Building Model

  K. Li, Y. Deng, Y. Kong, D. Liu, J. Chen, Y. Meng, J. Ma, C. Wang · IEEE Transactions on Geoscience and Remote Sensing · 2024

• PolyFootNet: Extracting Polygonal Building Footprints in Off-Nadir Remote Sensing Images

  K. Li, Y. Deng, J. Chen, Y. Meng, Z. Xi, J. Ma, C. Wang, M. Wang, X. Zhao · IEEE Transactions on Geoscience and Remote Sensing · 2025

• DragOSM: Extract Building Roofs and Footprints from Aerial Images by Aligning Historical Labels

  K. Li, X. Weng, Y. Deng, Y. Meng, C. Pang, G.-S. Xia, X. Zhao · arXiv preprint arXiv:2509.17951 · 2025

• ObliCity: A Benchmark and Baseline for Roof-to-Ground Projection Displacement Correction

  K. Li, Y. Deng, L. Deng, Z. Xi, C. Wang, J. Zhang, Y. Ji, Y. Meng, X. Zhao · arXiv preprint arXiv:2607.25210 · 2026

• LODEOT: Low-Dimensional and Efficient Offset Tokens for Building Footprint Extraction from Off-Nadir Imagery

  K. Li, et al. · 2025

• Scenix: Sparse-View 3D Scene Reconstruction via Executable Scene Programs

  K. Li, L. Jiang, Z. Li, J. Dong, J. Zhang, Y. Yin, R. Zhang, K. Yan, X. Huang, et al. · arXiv preprint arXiv:2608.07012 · 2026

• Reinforcement-Learning-Driven, Sparse-View-Consistent Indoor Scene Reconstruction基于强化学习的稀疏视角一致性室内场景重建

  On Working研究中

• Memory Mechanisms for Video World Models视频世界模型的记忆机制

  On Working研究中

• Remote-Sensing City Layout Extraction with MLLM

  Z. Zhou, K. Li, Y. Deng. arXiv preprint arXiv:2608.16484, 2026.

• ConsistNav: Closing the Action Consistency Gap in Zero-Shot Object Navigation with Semantic Executive Control

  H. Wang, Z. Li, Y. Zhang, Z. He, L. Jiang, K. Li, Y. Zhao, L. Fan, W. Hou, T. Liang, et al. arXiv preprint arXiv:2605.09869, 2026.

• DGTRSD and DGTRSCLIP: A Dual-Granularity Remote Sensing Image-Text Dataset and Vision-Language Foundation Model for Alignment

  W. Chen, Y. Deng, W. Jin, J. Chen, J. Chen, Y. Feng, Z. Xi, D. Liu, K. Li, Y. Meng. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), 2025.

• IRSAMap: Towards Large-Scale, High-Resolution Land Cover Map Vectorization

  Y. Meng, L. Deng, Z. Xi, J. Chen, J. Chen, A. Yue, D. Liu, K. Li, C. Wang, K. Li, et al. IEEE Transactions on Geoscience and Remote Sensing, 2025.

• PCP: A Prompt-Based Cartographic-Level Polygonal Vector Extraction Framework for Remote Sensing Images

  C. Wang, Z. Xi, D. Liu, Y. Feng, Y. Deng, K. Li, J. Chen, J. Chen, Y. Meng. IEEE Transactions on Geoscience and Remote Sensing, 2025.

• LRSCLIP: A Vision-Language Foundation Model for Aligning Remote Sensing Image with Longer Text

  W. Chen, J. Chen, Y. Deng, J. Chen, Y. Feng, Z. Xi, D. Liu, K. Li, Y. Meng. arXiv preprint arXiv:2503.19311, 2025.

• SayAnything: Audio-Driven Lip Synchronization with Conditional Video Diffusion

  J. Ma, S. Wang, J. Yang, J. Hu, J. Liang, G. Lin, K. Li, Y. Meng. arXiv preprint arXiv:2502.11515, 2025.

• CusMer: Multimodal Intent Recognition in Customer Service via Data Augment and LLM Merge

  Z. Li, B. Wu, Y. Zhang, X. Li, K. Li, W. Chen. Companion Proceedings of the ACM Web Conference (WWW Companion), 2025, pp. 3058-3062.

• SAMPolyBuild: Adapting the Segment Anything Model for polygonal building extraction

  C. Wang, J. Chen, Y. Meng, Y. Deng, K. Li, Y. Kong. ISPRS Journal of Photogrammetry and Remote Sensing, 2024, 218: 707-720.

• 基于边界曲线的多因素机场出租车管理系统模型

  程荟璇, 贺益鑫, 李锴, 覃思义. 实验科学与技术, 2022, 20(5): 40-44.

• Land Price Assessment Based on Deep Neural Network

  A. Hou, J. Liu, Y. Tao, S. Jiang, K. Li, Z. Zheng, J. Xia, Y. He, M. Zhu, G. Zhou, et al. IGARSS 2019, Yokohama, Japan.

• Urban Functional Regions Discovering Based on Deep Learning

  F. Mou, R. Kong, K. Li, Z. Zheng, J. Xia, Y. He, M. Zhu, G. Zhou, H. Zhang, Z. Liu, et al. IGARSS 2019, Yokohama, Japan, pp. 9462-9465.

• A WordNet-Based Geospatial Web Services Search Method Supporting Quality of Service Constraints

  L. Jiang, K. Li, D. Liu, Y. Zhou, Z. Zheng, F. Huang. IGARSS 2019, Yokohama, Japan, pp. 863-866.

Awards & Honours获奖与荣誉

Skills技能