2022 - 2026
Zhejiang University
Ph.D., Computer Science
Lab: Om AI and ACES.
Focus: Remote Sensing Vision-Language Models.
Advisor: Prof. Jianwei Yin, Tiancheng Zhao, and Yongheng Shang.
Zilun Zhang
I work on remote sensing vision-language models, UHR remote sensing imagery analysis, geospatial reasoning, few-shot learning, UAV search and rescue, and UE simulation.
Background
Education
2020 - 2022
University of Toronto
M.Eng., Analytics and Robotics
Lab: Intelligent Medical Image Computing Systems (IMICS) Lab.
Advisor: Prof. Farzad Khalvati.
2014 - 2019
University of Toronto
Honours B.Sc., Mathematics and its Applications, Computer Science, and Statistical Science
Lab: EcoSystem Lab.
Research Supervisor: Prof. Gennady Pekhimenko.
Focus
Research Interests
Remote Sensing Vision-Language Models
Ultrahigh-Resolution Remote Sensing Analysis
Few-Shot Learning
UAV Search and Rescue
Unreal Engine Simulation
I have served as a reviewer for journals and conferences including ISPRS JPRS, GRSM, TGRS, GRSL, ESWA, NeurIPS, CVPR, ICCV, ECCV, AAAI, MM, ACL and EMNLP.
Research
Selected Work
RS5M and GeoRSCLIP
TGRS 2024Built a 5-million-scale remote sensing image-text dataset and a CLIP-style model for zero-shot classification, cross-modal retrieval, and semantic localization in remote sensing.
RepositoryImageRAG
GRSM 2025Proposed a retrieval-augmented framework for ultrahigh-resolution remote sensing imagery, selecting relevant visual contexts before multimodal generation.
RepositoryGeo-R1
ISPRS JPRS 2026Developed a reasoning-oriented reinforcement fine-tuning approach for few-shot geospatial referring expression understanding.
RepositorySRMF
TGRS 2025Advanced long-tail ultrahigh-resolution satellite image segmentation with data augmentation and multimodal fusion.
RepositoryDetailCLIP
ICASSP 2026 PosterInjected fine-grained image details into CLIP feature space for multimodal retrieval on small and visually subtle targets.
RepositoryTGSFT
ICASSP 2026 OralPreserved knowledge in large language models through model-agnostic intrinsic generative replay for mitigating catastrophic forgetting.
RepositoryVLM-R1
arXiv 2025Contributed to a stable and generalizable R1-style vision-language reasoning model.
RepositoryPublications
Selected Publication
- Zilun Zhang, Tiancheng Zhao, Yulong Guo, and Jianwei Yin. "RS5M and GeoRSCLIP: A Large-Scale Vision-Language Dataset and a Large Vision-Language Model for Remote Sensing." IEEE Transactions on Geoscience and Remote Sensing (IF=8.6), 2024. Cited 350+ times.
- Zilun Zhang, Haozhan Shen, Tiancheng Zhao, Zian Guan, Bin Chen, Yuhao Wang, Xu Jia, Yuxiang Cai, Yongheng Shang, and Jianwei Yin. "Enhancing Ultrahigh Resolution Remote Sensing Imagery Analysis with ImageRAG: A New Framework." IEEE Geoscience and Remote Sensing Magazine (IF=16.4), 2025.
- Zilun Zhang, Zian Guan, Tiancheng Zhao, Haozhan Shen, Yuxiang Cai, Zhonggen Su, Yongheng Shang, Zhaojun Liu, Jianwei Yin, and Xiang Li. "Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning." ISPRS Journal of Photogrammetry and Remote Sensing (IF=12.2), 2026.
- Zilun Zhang, Cuifeng Shen, Yuan Shen, Yutao Sun, Xinyu Zhou, Huixin Xiong, Tiancheng Zhao, and Jianwei Yin. "DetailCLIP: Injecting Image Details into CLIP's Feature Space." IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2026.
- Zilun Zhang, Yutao Sun, Tiancheng Zhao, Leigang Sha, Ruochen Xu, Kyusong Lee, and Jianwei Yin. "Preserving Knowledge in Large Language Models Via Model-Agnostic Intrinsic Generative Replay." IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2026. Oral.
- Zilun Zhang, Peng Liu, Haozhan Shen, Tiancheng Zhao, Zhaojun Liu, and Jianwei Yin. "Effective Reinforcement Learning for Remote Sensing Vision-Language Models via Supervised Knowledge Injection." IEEE Transactions on Geoscience and Remote Sensing (IF=8.6), 2026.
- Yulong Guo*, Zilun Zhang*, Yongheng Shang, Tiancheng Zhao, Shuiguang Deng, Yingchun Yang, and Jianwei Yin. "SRMF: A Data Augmentation and Multimodal Fusion Approach for Long-Tail UHR Satellite Image Segmentation." IEEE Transactions on Geoscience and Remote Sensing (IF=8.6), 2025. Co-first author.
- Yue Zhou, Jue Chen, Zilun Zhang, Penghui Huang, Ran Ding, Zhentao Zou, Pengfei Gao, et al. "DVGBench: Implicit-to-Explicit Visual Grounding Benchmark in UAV Imagery with Large Vision-Language Models." ISPRS Journal of Photogrammetry and Remote Sensing (IF=12.2), 2026.
- Haozhan Shen, Kangjia Zhao, Tiancheng Zhao, Ruochen Xu, Zilun Zhang, Mingwei Zhu, and Jianwei Yin. "ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration." Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025. Oral.
- Haozhan Shen, Peng Liu, Jingcheng Li, Chunxin Fang, Yibo Ma, Jiajia Liao, Qiaoli Shen, Zilun Zhang, et al. "VLM-R1: A Stable and Generalizable R1-Style Large Vision-Language Model." arXiv preprint arXiv:2504.07615, 2025.
- Yutao Sun, Mingshuai Chen, Tiancheng Zhao, Ruochen Xu, Zilun Zhang, and Jianwei Yin. "The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding?" Findings of the Association for Computational Linguistics: ACL 2025, 2025.
- Xu Jia, Bin Chen, Huaxiao Zhou, Xiaochu Chen, Lingxin Yu, Zilun Zhang, and Yuxiang Cai. "TSAVD-CLIP: One Visual Encoder Learns Both Temporal and Spatial Features." Service Oriented Computing and Applications (IF=1.7), 2025.
- Yongheng Shang, Haiyu He, Zilun Zhang, Xiaoyu Zhang, Zhengwei Shen, Jianwei Yin, and Xiaoye Miao. "Methods for Monitoring the Photovoltaic Panel: A Review." International Conference on Agro-Geoinformatics, 2024.
- Zhuofan Cui, Pengwei Zhou, Xiaolong Wang, Zilun Zhang, Yingxuan Li, Hongbo Li, and Yu Zhang. "A Novel Geo-Localization Method for UAV and Satellite Images Using Cross-View Consistent Attention." Remote Sensing (IF=4.1), 2023.
- Ling Yang, Liangliang Li, Zilun Zhang, Xinyu Zhou, Erjin Zhou, and Yu Liu. "DPGN: Distribution Propagation Graph Network for Few-Shot Learning." CVPR, 2020.
Experience
Research and Industry
Megvii Research
Algorithm Engineer Intern
Jul 2019 - Aug 2022
Worked on few-shot learning, long-tail recognition, multimodal retrieval, and model distillation. Contributed to DPGN, accepted at CVPR 2020.
Alibaba DAMO Academy
Algorithm Engineer Intern
May 2018 - Aug 2018
Explored AI music generation and query-by-humming retrieval with sequence models, clustering, and ranking methods.
aUToronto (Autodrive Team), University of Toronto
Object Detection Group Member
Jan 2019 - Jun 2019
Data Science Team, University of Toronto
Undergraduate Member
Oct 2017 - Jun 2019