RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation
为解决遥感代理领域知识不足的问题，提出RSMeM机制，通过层级知识接地和失败感知经验提炼方法增强代理的知识和执行能力。
0 citationsRead paper
Selected work
Representative Papers
EarthEmbeddingExplorer: A Web Application for Cross-Modal Retrieval of Global Satellite Images
This work addresses the challenge of transforming Earth observation foundation models and their associated embeddings into open, accessible scientific tools that support cross-modal retrieval and discovery. The authors present a cloud-native, interactive web platform that, for the first time, publicly provides precomputed embeddings for global satellite imagery. The system integrates three complementary query modalities—natural language, image similarity, and geographic coordinates—enabling efficient, low-barrier, multimodal search over remote sensing data. By bridging the gap between advanced academic models and real-world applications, the platform significantly enhances the accessibility and scientific utility of Earth observation data at a global scale.
0 citationsRead paper
Recent publications
Latest Papers
RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation
为解决遥感代理领域知识不足的问题，提出RSMeM机制，通过层级知识接地和失败感知经验提炼方法增强代理的知识和执行能力。
0 citationsRead paper
EarthEmbeddingExplorer: A Web Application for Cross-Modal Retrieval of Global Satellite Images
This work addresses the challenge of transforming Earth observation foundation models and their associated embeddings into open, accessible scientific tools that support cross-modal retrieval and discovery. The authors present a cloud-native, interactive web platform that, for the first time, publicly provides precomputed embeddings for global satellite imagery. The system integrates three complementary query modalities—natural language, image similarity, and geographic coordinates—enabling efficient, low-barrier, multimodal search over remote sensing data. By bridging the gap between advanced academic models and real-world applications, the platform significantly enhances the accessibility and scientific utility of Earth observation data at a global scale.
0 citationsRead paper