# When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning

arXiv: https://arxiv.org/abs/2503.07588 · HTML: https://mlsanity.com/paper/2503.07588/

## Key facts

- Cited by 35 papers in the map (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 79 of its 95 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- Efficient LLM inference and serving / [Visual token pruning in multimodal models](https://mlsanity.com/inference/visual-token-pruning-in-multimodal-models/)

## Builds on (most cited first, 30 of 79)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models](https://mlsanity.com/paper/2403.06764/) (2024)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs](https://mlsanity.com/paper/2312.14135/) (2023)
- [LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models](https://mlsanity.com/paper/2403.15388/) (2024)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)
- [Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models](https://mlsanity.com/paper/2403.18814/) (2024)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models](https://mlsanity.com/paper/2311.06607/) (2023)
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [VisionZip: Longer is Better but Not Necessary in Vision Language Models](https://mlsanity.com/paper/2412.04467/) (2024)
- [PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction](https://mlsanity.com/paper/2410.17247/) (2024)
- [MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?](https://mlsanity.com/paper/2408.13257/) (2024)

## Built on by (most cited first, 30 of 35)

- [GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution](https://mlsanity.com/paper/2505.21375/) (2025)
- [RSVLM-QA: A Benchmark Dataset for Remote Sensing Vision Language Model-based Question Answering](https://mlsanity.com/paper/2508.07918/) (2025)
- [GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes](https://mlsanity.com/paper/2511.22645/) (2025)
- [Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Search](https://mlsanity.com/paper/2511.20460/) (2025)
- [A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs](https://mlsanity.com/paper/2512.17319/) (2025)
- [GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2602.14201/) (2026)
- [GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensing](https://mlsanity.com/paper/2604.08896/) (2026)
- [VICoT-Agent: A Vision-Interleaved Chain-of-Thought Framework for Interpretable Multimodal Reasoning and Scalable Remote Sensing Analysis](https://mlsanity.com/paper/2511.20085/) (2025)
- [Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding](https://mlsanity.com/paper/2602.14225/) (2026)
- [Seeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote Sensing](https://mlsanity.com/paper/2603.02754/) (2026)
- [Co-Training Vision Language Models for Remote Sensing Multi-task Learning](https://mlsanity.com/paper/2511.21272/) (2025)
- [FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2512.24022/) (2025)
- [OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks](https://mlsanity.com/paper/2603.09471/) (2026)
- [OSMDA: OpenStreetMap-based Domain Adaptation for Remote Sensing VLMs](https://mlsanity.com/paper/2603.11804/) (2026)
- [Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification](https://mlsanity.com/paper/2601.20742/) (2026)
- [NeSy-Route: A Neuro-Symbolic Benchmark for Constrained Route Planning in Remote Sensing](https://mlsanity.com/paper/2603.16307/) (2026)
- [Agentic AI for Remote Sensing: Technical Challenges and Research Directions](https://mlsanity.com/paper/2604.24919/) (2026)
- [WeaveEarth: Structured Evidence Construction and Reasoning for Training-Free UHR Remote Sensing Understanding](https://mlsanity.com/paper/2607.10120/) (2026)
- [Remote Sensing Image Intelligent Interpretation with the Language-Centered Perspective: Principles, Methods and Challenges](https://mlsanity.com/paper/2508.06832/) (2025)
- [UAV traffic scene understanding: A regulation embedded multi-modal network and a unified benchmark](https://mlsanity.com/paper/2603.10722/) (2026)
- [Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding](https://mlsanity.com/paper/2604.11122/) (2026)
- [UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing](https://mlsanity.com/paper/2604.13565/) (2026)
- [Beyond Zooming: Learning Multi-Tool Visual Reasoning for Ultra-High-Resolution Remote Sensing](https://mlsanity.com/paper/2607.25993/) (2026)
- [Cross-modal Context-aware Learning for Visual Prompt Guided Multimodal Image Understanding in Remote Sensing](https://mlsanity.com/paper/2512.11680/) (2025)
- [GeoVista: Visually Grounded Active Perception for Vision-Language Understanding of Ultra-High-Resolution Remote Sensing Images](https://mlsanity.com/paper/2605.14475/) (2026)
- [Text-RSIR: A Text-Guided Framework for Efficient Remote Sensing Image Transmission and Reconstruction](https://mlsanity.com/paper/2605.15558/) (2026)
- [SkyNative: A Native Multimodal Architecture for Remote Sensing Vision-Language Understanding](https://mlsanity.com/paper/2605.17949/) (2026)
- [MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation](https://mlsanity.com/paper/2607.06552/) (2026)
- [More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe](https://mlsanity.com/paper/2607.15942/) (2026)
- [SA-GEM: Scale-Adaptive and Geospatial Evidence-Modulated Token Pruning for Efficient Remote Sensing Large Vision-Language Models](https://mlsanity.com/paper/2608.15075/) (2026)

## Abstract (arXiv)

Efficient vision-language understanding of large Remote Sensing Images (RSIs) is meaningful but challenging. Current Large Vision-Language Models (LVLMs) typically employ limited pre-defined grids to process images, leading to information loss when handling gigapixel RSIs. Conversely, using unlimited grids significantly increases computational costs. To preserve image details while reducing computational complexity, we propose a text-guided token pruning method with Dynamic Image Pyramid (DIP) integration. Our method introduces: (i) a Region Focus Module (RFM) that leverages text-aware region localization capability to identify critical vision tokens, and (ii) a coarse-to-fine image tile selection and vision token pruning strategy based on DIP, which is guided by RFM outputs and avoids directly processing the entire large imagery. Additionally, existing benchmarks for evaluating LVLMs' perception ability on large RSI suffer from limited question diversity and constrained image sizes. We construct a new benchmark named LRS-VQA, which contains 7,333 QA pairs across 8 categories, with image length up to 27,328 pixels. Our method outperforms existing high-resolution strategies on four datasets using the same data. Moreover, compared to existing token reduction methods, our approach demonstrates higher efficiency under high-resolution settings. Dataset and code are in https://github.com/VisionXLab/LRS-VQA.