The rapid advancement of foundation models has revolutionized visual representation learning in a self-supervised manner. However, their application in remote sensing (RS) remains constrained by a fundamental gap: existing models predominantly handle single or limited modalities, overlooking the inherently multi-modal nature of RS observations. Optical, synthetic aperture radar (SAR), and multi-spectral data offer complementary insights that significantly reduce the inherent ambiguity and uncertainty in single-source analysis. To bridge this gap, we introduce RingMoE, a unified multi-modal RS foundation model with 14.7 billion parameters, pre-trained on 400 million multi-modal RS images from nine satellites. RingMoE incorporates three key innovations: 1) A hierarchical Mixture-of-Experts (MoE) architecture comprising modal-specialized, collaborative, and shared experts, effectively modeling intra-modal knowledge while capturing cross-modal dependencies to mitigate conflicts between modal representations; 2) Physics-informed self-supervised learning, explicitly embedding sensor-specific radiometric characteristics into the pre-training objectives; 3) Dynamic expert pruning, enabling adaptive model compression from 14.7B to 1B parameters while maintaining performance, facilitating efficient deployment in Earth observation applications. Evaluated across 23 benchmarks spanning six key RS tasks (i.e., classification, detection, segmentation, tracking, change detection, and depth estimation), RingMoE outperforms existing foundation models and sets new SOTAs, demonstrating remarkable adaptability from single-modal to multi-modal scenarios. Beyond theoretical progress, it has been deployed and trialed in multiple sectors, including emergency response, land management, marine sciences, and urban planning.

Remote sensing foundation models largely break away from the traditional paradigm of designing task-specific models, offering greater scalability across multiple tasks. However, they face challenges such as low computational efficiency and limited interpretability, especially when dealing with large-scale remote sensing images. To overcome these, we draw inspiration from heat conduction, a physical process modeling local heat diffusion. Building on this idea, we are the first to explore the potential of using the parallel computing model of heat conduction to simulate the local region correlations in high-resolution remote sensing images, and introduce RS-vHeat, an efficient multi-modal remote sensing foundation model. Specifically, RS-vHeat 1) applies the Heat Conduction Operator (HCO) with a complexity of $O(N^{1.5})$ and a global receptive field, reducing computational overhead while capturing remote sensing object structure information to guide heat diffusion; 2) learns the frequency distribution representations of various scenes through a self-supervised strategy based on frequency domain hierarchical masking and multi-domain reconstruction; 3) significantly improves efficiency and performance over state-of-the-art techniques across 4 tasks and 10 datasets. Compared to attention-based remote sensing foundation models, we reduce memory usage by 84\%, FLOPs by 24\% and improves throughput by 2.7 times. The code will be made publicly available.

Recently, multimodal large language models (MLLMs) have shown excellent reasoning capabilities in various fields. Most of the existing remote sensing (RS) MLLMs solve image-level text generation problems (e.g., image captioning), but ignore the core issues of object-level recognition, location, and multitemporal changes in the field of RS. In this article, we propose RingMoGPT, a multimodal foundation model that unifies vision, language, and localization. Based on the idea of domain adaption, RingMoGPT can complete training by fine-tuning only a few parameters. To make the model capable of object detection and change captioning, we further propose a location- and instruction-aware querying transformer (Q-Former) and a change detection module, respectively. To improve the performance of RingMoGPT, we carefully design the pretraining dataset and the instruction-tuning dataset. The pretraining dataset contains over a half million high-quality image and text pairs, which are generated through a low-cost and efficient data generation paradigm. The instruction-tuning dataset contains more than 1.6 million question-answer pairs, including six downstream tasks: scene classification, object detection, visual question answering (VQA), image captioning, grounded image captioning, and change captioning. Our experiments show that RingMoGPT performs well on six tasks, especially its ability to analyze multitemporal data changes and identify dense objects. We also verified the model under a zero-shot setting, and the results show that the proposed RingMoGPT also has good generalization ability in the face of new data.

Recently, large-scale Vision-Language Models (VLMs) have gained widely attention in the field of remote sensing. However, the researching on VLM requires a substantial amount of data, which is relatively scarce in the remote sensing domain. To overcome this limitation, in this paper, we present ViGen500K, a larger and more challenging image-text dataset. Nearly 500,000 images have been collected, accompanied by over 1 million annotations to adapt to the diverse requirements of various image-text tasks in remote sensing. Besides, a promising, efficient, low-cost, and highly automated data annotation method is proposed to make our dataset could be easily extensive by keeping adding extra unlabeled remote sensing images. Theoretically, ViGen500K is an infinitely large dataset. From a quantitative point of view, compared with traditional image caption datasets, ViGen500K not only has more images but also covers more object categories, which enables the model trained on our dataset could have a wider range of target-text alignment capabilities. Several experiments have been conducted to provide benchmarks for our dataset.