SkyNative: A Native Multimodal Framework for Remote Sensing Visual Evidence Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910231760470016 |
|---|---|
| author | Yang, Xiao Fu, Ronghao Lin, Zhiwen Duan, Zhuoran Zhu, Jiashun Hu, Jiasen Sun, Lang Zhang, Weipeng Liu, Jiaqi Na, Xu Liu, Haoran Zhang, Weijie Yang, Bo |
| author_facet | Yang, Xiao Fu, Ronghao Lin, Zhiwen Duan, Zhuoran Zhu, Jiashun Hu, Jiasen Sun, Lang Zhang, Weipeng Liu, Jiaqi Na, Xu Liu, Haoran Zhang, Weijie Yang, Bo |
| contents | Remote sensing vision-language models commonly rely on pretrained visual encoders to convert images into semantic features before language-model reasoning. While effective for scene-level understanding, this pipeline may prematurely compress local visual evidence, making fine-grained spatial reasoning vulnerable to language priors, especially in ultra-high-resolution remote sensing imagery. We present SkyNative, a native multimodal framework for remote sensing that adopts an encoder-free architecture, removing the pretrained visual backbone to directly represent images as raw patch tokens in the language-model token space. To reconcile low-level visual patches with textual tokens, SkyNative introduces a modality-aware decoupling mechanism that uses modality-specific parameters within a unified autoregressive backbone. We further introduce a visual reliance benchmark that diagnoses whether models ground their answers in image evidence through progressive visual degradation and misleading textual prompts. Across standard remote sensing understanding tasks and large-format spatial reasoning evaluations, SkyNative shows stronger image-grounded perception and improved robustness against prompt-induced language priors. These results suggest that native patch-level multimodal modeling is a promising direction for reliable remote sensing vision-language reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_17949 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SkyNative: A Native Multimodal Framework for Remote Sensing Visual Evidence Reasoning Yang, Xiao Fu, Ronghao Lin, Zhiwen Duan, Zhuoran Zhu, Jiashun Hu, Jiasen Sun, Lang Zhang, Weipeng Liu, Jiaqi Na, Xu Liu, Haoran Zhang, Weijie Yang, Bo Computer Vision and Pattern Recognition Remote sensing vision-language models commonly rely on pretrained visual encoders to convert images into semantic features before language-model reasoning. While effective for scene-level understanding, this pipeline may prematurely compress local visual evidence, making fine-grained spatial reasoning vulnerable to language priors, especially in ultra-high-resolution remote sensing imagery. We present SkyNative, a native multimodal framework for remote sensing that adopts an encoder-free architecture, removing the pretrained visual backbone to directly represent images as raw patch tokens in the language-model token space. To reconcile low-level visual patches with textual tokens, SkyNative introduces a modality-aware decoupling mechanism that uses modality-specific parameters within a unified autoregressive backbone. We further introduce a visual reliance benchmark that diagnoses whether models ground their answers in image evidence through progressive visual degradation and misleading textual prompts. Across standard remote sensing understanding tasks and large-format spatial reasoning evaluations, SkyNative shows stronger image-grounded perception and improved robustness against prompt-induced language priors. These results suggest that native patch-level multimodal modeling is a promising direction for reliable remote sensing vision-language reasoning. |
| title | SkyNative: A Native Multimodal Framework for Remote Sensing Visual Evidence Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.17949 |