mlsanityData to 14 Oct 2026

EagleVision: Object-level Attribute Multimodal LLM for Remote Sensing

arXiv 2503.23330 ↗First posted 30 Mar 2025cs.CVcited by 8

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

Abstract (arXiv)

Recent advances in multimodal large language models (MLLMs) have demonstrated impressive results in various visual tasks. However, in remote sensing (RS), high resolution and small proportion of objects pose challenges to existing MLLMs, which struggle with object-centric tasks, particularly in precise localization and fine-grained attribute description for each object. These RS MLLMs have not yet surpassed classical visual perception models, as they only provide coarse image understanding, leading to limited gains in real-world scenarios. To address this gap, we establish EagleVision, an MLLM tailored for remote sensing that excels in object detection and attribute comprehension. Equipped with the Attribute Disentangle module, EagleVision learns disentanglement vision tokens to express distinct attributes. To support object-level visual-language alignment, we construct EVAttrs-95K, the first large-scale object attribute understanding dataset in RS for instruction tuning, along with a novel evaluation benchmark, EVBench. EagleVision achieves state-of-the-art performance on both fine-grained object detection and object attribute understanding tasks, highlighting the mutual promotion between detection and understanding capabilities in MLLMs. The code, model, data, and demo will be available at https://github.com/XiangTodayEatsWhat/EagleVision.

Key facts. Cited by 8 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 50 of its 60 references that are in the map. First posted on arXiv 30 Mar 2025.

Builds on

50 of 60 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts7 Dec
  2. 2024LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model4 Feb
  3. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensing24 Nov
  4. 2023RSGPT: A Remote Sensing Vision Language Model and Benchmark28 Jul

Other references · 46

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2023Visual Instruction Tuningcited by 7,869
  7. 2020End-to-End Object Detection with Transformerscited by 7,414
  8. 2017Mask R-CNNcited by 7,277
  9. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  10. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  11. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  12. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
34 more
  1. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  2. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  3. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  4. 2024Qwen2 Technical Reportcited by 2,120
  5. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  6. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  7. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  8. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,319
  9. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,301
  10. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  11. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,239
  12. 2019Objects as Pointscited by 1,175
  13. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,005
  14. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  15. 2024InternLM2 Technical Reportcited by 397
  16. 2021Oriented R-CNN for Object Detectioncited by 231
  17. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 203
  18. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 195
  19. 2019R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Objectcited by 194
  20. 2020Align Deep Features for Oriented Object Detectioncited by 187
  21. 2017Arbitrary-Oriented Scene Text Detection via Rotation Proposalscited by 176
  22. 2023LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmarkcited by 169
  23. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  24. 2023PolyFormer: Referring Image Segmentation as Sequential Polygon Generationcited by 148
  25. 2021FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagerycited by 143
  26. 2019Gliding vertex on the horizontal bounding box for multi-oriented object detectioncited by 134
  27. 2021Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergencecited by 130
  28. 2024Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Modelscited by 119
  29. 2023LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Modelscited by 113
  30. 2020Fairness by Learning Orthogonal Disentangled Representationscited by 76
  31. 2022The KFIoU Loss for Rotated Object Detectioncited by 73
  32. 2024LSKNet: A Foundation Lightweight Backbone for Remote Sensingcited by 44
  33. 2023OvarNet: Towards Open-vocabulary Object Attribute Recognitioncited by 43
  34. 2024ChatRex: Taming Multimodal LLM for Joint Perception and Understandingcited by 30

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 4.

8 papers.

  1. 2025A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontierscited by 37
  2. 2026RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMscited by 8
  3. 2025DescribeEarth: Describe Anything for Remote Sensing Imagescited by 5
  4. 2025A Multimodal, Multilingual, and Multidimensional Pipeline for Fine-grained Crowdsourcing Earthquake Damage Evaluationcited by 3
  5. 2025Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AIcited by 3
  6. 2026RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observationcited by 2
  7. 2026RemoteZero: Geospatial Reasoning with Zero Labelscited by 2
  8. 2026Hierarchical Fine-Grained Aerial Object Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Multimodal Large Language Models for Remote Sensing Image Understanding: Domain-Specific or General-Purpose?
  2. 2025Foundation Models for Remote Sensing: An Analysis of MLLMs for Object Localization
  3. 2026SkyNative: A Native Multimodal Architecture for Remote Sensing Vision-Language Understanding
  4. 2025A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs
  5. 2025Bring Remote Sensing Object Detect Into Nature Language Model: Using SFT Method
  6. 2025A Vision Centric Remote Sensing Benchmark
  7. 2025GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing
  8. 2024SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model