# The Earth in One Gaze: Training-Free Active Focus for UHR Remote Sensing Understanding

arXiv: https://arxiv.org/abs/2609.31747 · HTML: https://mlsanity.com/paper/2609.31747/

## 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 39 of its 44 references that are in the map.
- First posted on arXiv 23 Sep 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, 30 of 39)

- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs](https://mlsanity.com/paper/2312.14135/) (2023)
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models](https://mlsanity.com/paper/2403.18814/) (2024)
- [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)
- [Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning](https://mlsanity.com/paper/2505.15966/) (2025)
- [RSGPT: A Remote Sensing Vision Language Model and Benchmark](https://mlsanity.com/paper/2307.15266/) (2023)
- [LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images](https://mlsanity.com/paper/2403.11703/) (2024)
- [EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain](https://mlsanity.com/paper/2401.16822/) (2024)
- [MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs](https://mlsanity.com/paper/2502.17422/) (2025)
- [LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model](https://mlsanity.com/paper/2402.02544/) (2024)
- [ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration](https://mlsanity.com/paper/2411.16044/) (2024)
- [VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis](https://mlsanity.com/paper/2403.20213/) (2024)
- [Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks](https://mlsanity.com/paper/1809.03355/) (2018)
- [EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering](https://mlsanity.com/paper/2312.12222/) (2023)
- [XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?](https://mlsanity.com/paper/2503.23771/) (2025)
- [HiLM-D: Enhancing MLLMs with Multi-Scale High-Resolution Details for Autonomous Driving](https://mlsanity.com/paper/2309.05186/) (2023)
- [GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution](https://mlsanity.com/paper/2505.21375/) (2025)
- [When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning](https://mlsanity.com/paper/2503.07588/) (2025)
- [FOVEA: Foveated Image Magnification for Autonomous Navigation](https://mlsanity.com/paper/2108.12102/) (2021)
- [Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG](https://mlsanity.com/paper/2503.01222/) (2025)
- [ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks](https://mlsanity.com/paper/2511.12267/) (2025)
- [AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition](https://mlsanity.com/paper/2512.03794/) (2025)
- [FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers](https://mlsanity.com/paper/2501.16297/) (2025)
- [Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models](https://mlsanity.com/paper/2509.22221/) (2025)
- [Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs](https://mlsanity.com/paper/2310.16033/) (2023)
- [Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping](https://mlsanity.com/paper/2510.09741/) (2025)
- [Learning to Zoom and Unzoom](https://mlsanity.com/paper/2303.15390/) (2023)
- [Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Search](https://mlsanity.com/paper/2511.20460/) (2025)

## Abstract (arXiv)

Multimodal large language models (MLLMs) must balance local detail against scene context when interpreting ultra-high-resolution (UHR) remote sensing (RS) imagery within a limited visual-input budget. Existing selection-based methods either prune tokens and select patches through relevance scoring, or crop actively through repeated inspection. Neither strategy directly redistributes pixels within a continuous full-scene view: the first retains selected tokens or patches, and the second re-encodes a crop detached from its surroundings. Our pilot study finds that a frozen MLLM already produces useful question-guided spatial requests, yet crop-based inspection of the selected regions does not consistently improve its answers. We therefore formulate UHR understanding as a question of where to spend a fixed pixel budget. Based on this, we introduce GazeEarth, a simple-yet-effective training-free framework that couples question-guided region selection with full-scene foveated observation. The MLLM selects evidence cells from an indexed overview; a deterministic, topology-preserving warp resamples the original image onto a fixed-size canvas, enlarging their shared neighborhood while compressing the periphery; the same frozen model answers from this focused view, using at most two MLLM calls and no external selector or iterative search. Across three UHR remote sensing benchmarks and four frozen backbones, GazeEarth improves benchmark-averaged accuracy by 4.6 to 9.4 percentage points over direct answering and 3.4 to 4.3 over overview answering, outperforming task-trained methods. Our analyses show that existing MLLMs can guide where to look in UHR images on their own, and that what they can infer from the selected evidence depends on how that evidence is presented.