Metraipolis › archive › dc_351afe501ae6
Aerial-R1: Reinforcing Aerial Reasoning and Segmentation in MLLMs — arXiv:2610.33056
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.33056
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:59:29.138Z
- SHA-256 of the archived text
de1b7d77a993c370049e9f39bd3c07cb9683d44f1579d0f3c5b17312ccdee96b- Stable URL of this page
https://metraipolis.com/documento/dc_351afe501ae6
How to cite
Aerial-R1: Reinforcing Aerial Reasoning and Segmentation in MLLMs — arXiv:2610.33056 — arXiv (en), https://arxiv.org/abs/2610.33056 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_351afe501ae6 (Metraipolis archive dc_351afe501ae6, sha256 de1b7d77a993c370049e9f39bd3c07cb9683d44f1579d0f3c5b17312ccdee96b)
BibTeX
@misc{dc351afe501ae6,
title = {Aerial-R1: Reinforcing Aerial Reasoning and Segmentation in MLLMs — arXiv:2610.33056},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.33056},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_351afe501ae6; sha256 de1b7d77a993c370049e9f39bd3c07cb9683d44f1579d0f3c5b17312ccdee96b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33056. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While Multimodal Large Language Models (MLLMs) have revolutionized general visual perception, existing methods suffer from severe hallucination in the aerial domain, where extreme scale variations and visual ambiguity abound. Existing Supervised Fine-Tuning (SFT) paradigms force models to mimic ground truth without modeling uncertainty, often resulting in blind guessing on tiny or unrecognizable objects in aerial scenes. In this paper, we present Aerial-R1, the first aerial MLLM framework to reinforce visual reasoning capabilities for aerial reasoning and segmentation. Drawing inspiration from the reasoning-incentivizing mechanisms of DeepSeek-R1, we find that trustworthy perception stems from consistency across views, establishing a visual parallel to the Chain-of-Thought in logic. To effectively adapt policy optimization for non-autoregressive mask generation, we introduce Hybrid-View Group Advantage-Weighted Regression (H-GAWR). This strategy constructs dynamic groups of high-resolution and low-resolution views, seamlessly bridging group-relative advantage estimation with advantage-weighted policy extraction. By enforcing consensus on clear inputs and strictly penalizing hallucinations on ambiguous ones, Aerial-R1 develops an explicitly incentivized refusal mechanism. Extensive experiments on VSAI-Ref, the first aerial MLLM benchmark dedicated to jointly evaluating dense reasoning and hallucination robustness, demonstrate that Aerial-R1 significantly outperforms SFT baselines in segmentation precision while substantially mitigating fatal hallucinations in low-information scenarios, paving the way for more reliable and trustworthy aerial agents. Codes are available on this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.33056 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-27T07:55:30.796Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).