mlsanityData to 7 Oct 2026

UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing

arXiv 2604.13565 ↗First posted 15 Apr 2026cs.CV cs.AIcited by 1

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

also in 1 more
Abstract (arXiv)

Ultra-high-resolution (UHR) remote sensing imagery couples kilometer-scale context with query-critical evidence that may occupy only a few pixels. Such vast spatial scale leads to a quadratic explosion of visual tokens and hinders the extraction of information from small objects. Previous works utilize direct downsampling, dense tiling, or global top-k pruning, which either compromise query-critical image details or incur unpredictable compute. In this paper, we propose UHR-BAT, a query-guided and region-faithful token compression framework to efficiently select visual tokens under a strict context budget. Specifically, we leverage text-guided, multi-scale importance estimation for visual tokens, effectively tackling the challenge of achieving precise yet low-cost feature extraction. Furthermore, by introducing region-wise preserve and merge strategies, we mitigate visual token redundancy, further driving down the computational budget. Experimental results show that UHR-BAT achieves state-of-the-art performance across various benchmarks. Code will be available at https://github.com/Yunkaidang/UHR.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 59 of its 71 references that are in the map. First posted on arXiv 15 Apr 2026.

Builds on

59 of 71 references.

Closest ancestors · 15

Same direction, newest first

  1. 2025FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensing30 Dec
  2. 2025A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs19 Dec
  3. 2025GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution27 May
  4. 2025XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?31 Mar
  5. 2025When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning10 Mar
  6. 2024EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues19 Dec
  7. 2024VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding18 Jun
  8. 2024SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding14 Jun
  9. 2024VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis29 Mar
  10. 2024LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model4 Feb
  11. 2024EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain30 Jan
  12. 2024SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model18 Jan
3 more
  1. 2023Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment12 Dec
  2. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensing24 Nov
  3. 2023RSGPT: A Remote Sensing Vision Language Model and Benchmark28 Jul

Other references · 44

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2023Segment Anythingcited by 8,158
  3. 2023Visual Instruction Tuningcited by 7,792
  4. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  5. 2025Qwen2.5-VL Technical Reportcited by 5,418
  6. 2024GPT-4o System Cardcited by 4,467
  7. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  8. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  9. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  10. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  11. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  12. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
32 more
  1. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  2. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  3. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  4. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  5. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  6. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,224
  7. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  8. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  9. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,061
  10. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,000
  11. 2023A Survey on Multimodal Large Language Modelscited by 898
  12. 2024DeepSeek-VL: Towards Real-World Vision-Language Understandingcited by 718
  13. 2023VILA: On Pre-training for Visual Language Modelscited by 686
  14. 2024Phi-4 Technical Reportcited by 675
  15. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  16. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 545
  17. 2022SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagerycited by 402
  18. 2023InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Compositioncited by 297
  19. 2024InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Outputcited by 195
  20. 2023Multimodal Large Language Models: A Surveycited by 193
  21. 2024LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Imagescited by 193
  22. 2024MobileVLM V2: Faster and Stronger Baseline for Vision Language Modelcited by 172
  23. 2024InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HDcited by 156
  24. 2024LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Modelcited by 128
  25. 2024Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Modelscited by 112
  26. 2023TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbonescited by 77
  27. 2024Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Surveycited by 52
  28. 2025Scaling Vision Pre-Training to 4K Resolutioncited by 26
  29. 2024Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarioscited by 19
  30. 2025ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Taskscited by 19
  31. 2025Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Searchcited by 11
  32. 2026HART: High-Resolution Annotation-Free Reasoning Technique through a Closed-loop Frameworkcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026RS-OPSD: Reliable Privileged On-Policy-Self-Distillation for Ultra-High-Resolution Remote Sensing VQAcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026UHR-DETR: Efficient End-to-End Small Object Detection for Ultra-High-Resolution Remote Sensing Imagery
  2. 2026Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding
  3. 2024ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG
  4. 2026The Earth in One Gaze: Training-Free Active Focus for UHR Remote Sensing Understanding
  5. 2026WeaveEarth: Structured Evidence Construction and Reasoning for Training-Free UHR Remote Sensing Understanding
  6. 2026PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Dataset
  7. 2026GeoVista: Visually Grounded Active Perception for Vision-Language Understanding of Ultra-High-Resolution Remote Sensing Images
  8. 2026SA-GEM: Scale-Adaptive and Geospatial Evidence-Modulated Token Pruning for Efficient Remote Sensing Large Vision-Language Models