DualComp uses a lightweight router to split visual token compression into a semantic stream with size-adaptive clustering and a geometric stream with path-tracing recovery, enabling low-cost high-fidelity UHR remote sensing interpretation.
arXiv preprint arXiv:2506.01667 (2025), https://arxiv.org/abs/2506.016675
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
baseline 1
dataset 1
citation-polarity summary
representative citing papers
UniGeoSeg releases the first million-scale dataset for instruction-driven remote sensing segmentation and a unified model that achieves state-of-the-art results with strong zero-shot generalization.
A tri-modal model with LLM-generated text from MRIs and a vision-guided dual alignment fusion module achieves state-of-the-art performance on real-world ischemic stroke prognosis prediction.
Agentic AI faces structural challenges in remote sensing due to geospatial data properties and workflow constraints, requiring EO-native agents built around structured state, tool-aware reasoning, and validity-aware evaluation.
The BDGF framework balances diffusion features to guide multi-branch networks with mutual learning and achieves superior land-cover classification performance on four multimodal remote sensing datasets.
The paper delivers a unified review and roadmap of Earth science foundation models, structured by capability depth from perception to agentic reasoning and by application breadth across atmosphere, hydrosphere, lithosphere, biosphere, anthroposphere, and cryosphere, while compiling over 200 datasets
citing papers explorer
-
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding
DualComp uses a lightweight router to split visual token compression into a semantic stream with size-adaptive clustering and a geometric stream with path-tracing recovery, enabling low-cost high-fidelity UHR remote sensing interpretation.
-
UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes
UniGeoSeg releases the first million-scale dataset for instruction-driven remote sensing segmentation and a unified model that achieves state-of-the-art results with strong zero-shot generalization.
-
Vision-Core Guided Contrastive Learning for Balanced Multi-modal Prognosis Prediction of Stroke
A tri-modal model with LLM-generated text from MRIs and a vision-guided dual alignment fusion module achieves state-of-the-art performance on real-world ischemic stroke prognosis prediction.
-
Agentic AI for Remote Sensing: Technical Challenges and Research Directions
Agentic AI faces structural challenges in remote sensing due to geospatial data properties and workflow constraints, requiring EO-native agents built around structured state, tool-aware reasoning, and validity-aware evaluation.
-
Balanced Diffusion-Guided Fusion for Multimodal Remote Sensing Classification
The BDGF framework balances diffusion features to guide multi-branch networks with mutual learning and achieves superior land-cover classification performance on four multimodal remote sensing datasets.
-
Earth Science Foundation Models: From Perception to Reasoning and Discovery
The paper delivers a unified review and roadmap of Earth science foundation models, structured by capability depth from perception to agentic reasoning and by application breadth across atmosphere, hydrosphere, lithosphere, biosphere, anthroposphere, and cryosphere, while compiling over 200 datasets