Multi-Modal LLMs
Vision-language models that align imagery with text: multimodal pre-training and instruction tuning, in-context learning, model compression and pruning, and benchmarks that measure what these models actually understand.
Learn more Scroll to explore
Building machines that perceive and reason — at the crossroads of vision, language and remote sensing
Led by Dr. Wenjia Xu, our group works at the intersection of computer vision, natural language processing and remote sensing, with a focus on multi-modal large language models, agents, and few-shot learning.
What we work on
View ResearchFour research lines: the multi-modal models themselves, the agents built on top of them, the LEO communication systems that carry the data, and the Earth observation problems all of it is meant to solve.
Agent
Autonomous systems that plan, call tools and verify their own work — hierarchical multi-agent architectures for long-horizon tasks, tool-augmented reasoning, and agents that operate real analysis pipelines end to end.
Learn more
Intelligence for LEO Communication and Network
Learning-based signal and network intelligence for low-Earth-orbit systems: specific emitter identification, intelligent signal processing, and the integration of communication with remote sensing on a single platform.
Learn more
Earth Observation Applications
Turning satellite and UAV observations into usable measurements: scene classification, change detection, height and depth estimation, multi-view stereo, and UAV visual localization.
Learn moreThe people doing the work
View TeamA small group in Beijing, working on models that read the Earth from orbit
Wenjia Xu 许文嘉
Associate Professor · PhD Supervisor
School of Information and Communication Engineering, BUPT
Research across computer vision, natural language processing and remote sensing, focusing on agents, multimodal large language models and few-shot learning.
Computer Vision Natural Language Processing Remote Sensing
1,370+ Total citations
h-index 18 Google Scholar
40+ Publications
Students & alumni
19 Members
6 PhD Students
13 Master Students
5 Alumni
Hongyu Wang PhD Student 
Siyuan Wan PhD Student 
Ruiqing Yu PhD Student 
Xun Li PhD Student 
Yuhuan Huang PhD Student 
Yuxin He PhD Student 
Shuoyuan Sun Master Student 
Boyang Mu Master Student 
Bowen Lu Master Student 
Mudi Zhu Master Student 
Yujie Li Master Student 
Minghao Xue Master Student 
Xuhao Chen Master Student 
Shengjie Qin Master Student 
Guoyan Sun Master Student 
Chengwen Zheng Master Student 
Shengxian Wang Master Student 
Zhishan Zou Master Student 
Kailu Zhang Master Student We train researchers who can take a problem from a raw satellite signal all the way to a working system — and who leave the lab with the judgement to pick the next problem themselves.
Adequate computational power support Global collaboration network Cutting-edge scientific questions
Featured News
View NewsFollow our latest publications, awards, field activities, student achievements, and research updates from IntelliSense Lab.
Latest Publications
View publicationsOur latest work in computer vision, language intelligence, multi-modal learning, and remote sensing.
RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent
Science China Information Sciences
View Details
Life beyond research
Dinners, outings and the conferences we travelled to together — the part of lab life that does not show up in a paper.
