# SkyNative: A Native Multimodal Architecture for Remote Sensing Vision-Language Understanding

arXiv: https://arxiv.org/abs/2605.17949 · HTML: https://mlsanity.com/paper/2605.17949/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 18 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification](https://mlsanity.com/paper/1608.05167/) (2016)
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?](https://mlsanity.com/paper/2408.13257/) (2024)
- [RSVQA: Visual Question Answering for Remote Sensing Data](https://mlsanity.com/paper/2003.07333/) (2020)
- [FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding](https://mlsanity.com/paper/2012.02951/) (2020)
- [VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding](https://mlsanity.com/paper/2406.12384/) (2024)
- [SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding](https://mlsanity.com/paper/2406.10100/) (2024)
- [VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis](https://mlsanity.com/paper/2403.20213/) (2024)
- [EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues](https://mlsanity.com/paper/2412.15190/) (2024)
- [GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing](https://mlsanity.com/paper/2501.13925/) (2025)
- [GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution](https://mlsanity.com/paper/2505.21375/) (2025)
- [VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models](https://mlsanity.com/paper/2405.16919/) (2024)
- [When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning](https://mlsanity.com/paper/2503.07588/) (2025)
- [ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks](https://mlsanity.com/paper/2511.12267/) (2025)
- [Foundation Models in Remote Sensing: Evolving from Unimodality to Multimodality](https://mlsanity.com/paper/2603.00988/) (2026)
- [BREEN: Bridge Data-Efficient Encoder-Free Multimodal Learning with Learnable Queries](https://mlsanity.com/paper/2503.12446/) (2025)
- [OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks](https://mlsanity.com/paper/2603.09471/) (2026)

## Abstract (arXiv)

Remote sensing vision-language models (RS-VLMs) commonly employ a pretrained vision encoder and a projection module to map image features into the token space of a large language model. Although effective, this modular RS-VLMs separates visual representation from language reasoning, potentially limiting the direct involvement of fine-grained visual evidence in complex spatial inference. This challenge is particularly relevant to remote sensing imagery, which often covers broad geographic areas and contains multi-scale objects, dense target distributions, and intricate spatial layouts. In this paper, we propose SkyNative, the first study to explore a native multimodal architecture for remote sensing vision-language tasks. SkyNative converts remote sensing images into visual tokens through a lightweight patch embedding module and places them together with text tokens in a shared autoregressive sequence, allowing textual tokens to directly access the preceding visual context. To accommodate the heterogeneous characteristics of the two modalities, we further adopt a modality-aware decoupling mechanism that applies modality-specific projections, normalization, and feed-forward transformations while processing both modalities through shared causal self-attention. Extensive experiments demonstrate SkyNative's strong capabilities in dense small-object perception, large-format contextual understanding, complex reasoning, and robustness, with scores of 68.93%, 47.40%, and 63.43% on HRRSD, RSHR reasoning, and OmniEarth, respectively. These results suggest that the native VLM architecture explored in SkyNative represents a promising approach to RS vision-language modeling.