Multi-modal LLMs & Agents
Vision-language multi-modal LLMs, in-context learning, model compression and pruning, and agent systems for real-world tasks such as remote sensing.
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.
The scientific questions we address
View ResearchOur work spans vision, language and remote sensing, organized around perception, understanding and decision-making.
Few-shot / Zero-shot Learning
Attribute prototype networks and visual-semantic embeddings that recognize novel categories from few or zero labeled samples.
Learn more
Vision-Language Understanding
Image captioning, distinctive captioning and visual-semantic alignment - so models not only see, but describe.
Learn more
Remote Sensing Intelligence
Super-resolution, UAV visual localization, height estimation and change detection for Earth observation and sustainability.
Learn morePeople behind these scientific questions
View TeamWe are driven by creativity and curiosity to push back the frontiers of knowledge
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 & research assistants
7 Members
2 PhD Students
3 Master Students
2 Research Assistants
Explore critical questions in Earth observation with outstanding collaborators, turning remote sensing data into knowledge for a more sustainable future.
Adequate computational power support Global collaboration network Cutting-edge scientific questions
Moments across Earth
Fieldwork, conferences and the moments that connect our team across the world.
Featured News
View NewsFollow our latest publications, awards, field activities, student achievements, and research updates from IntelliSensing Lab.
Latest Publications
View publicationsOur latest work in computer vision, language intelligence, multi-modal learning, and remote sensing.
RayZer: A Self-supervised Large View Synthesis Model
ICCV, 2025 (Best Student Paper Honorable Mention, Best Paper Candidate, Oral Presentation)
View DetailsLatest Blogs
View blogsResearch notes, technical reflections, and ideas taking shape inside IntelliSensing Lab.