mlsanityData to 14 Oct 2026

MarsRetrieval: Benchmarking Vision-Language Models for Planetary-Scale Geospatial Retrieval on Mars

arXiv 2602.13961 ↗First posted 15 Feb 2026cs.CV astro-ph.IM cs.CLcited by 0

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

Abstract (arXiv)

Data-driven approaches like deep learning are rapidly advancing planetary science, particularly in Mars exploration. Despite recent progress, most existing benchmarks remain confined to closed-set supervised visual tasks and do not support text-guided retrieval for geospatial discovery. We introduce MarsRetrieval, a retrieval benchmark for evaluating vision-language models for Martian geospatial discovery. MarsRetrieval includes three tasks: (1) paired image-text retrieval, (2) landform retrieval, and (3) global geo-localization, covering multiple spatial scales and diverse geomorphic origins. We propose a unified retrieval-centric protocol to benchmark multimodal embedding architectures, including contrastive dual-tower encoders and generative vision-language models. Our evaluation shows MarsRetrieval is challenging: even strong foundation models often fail to capture domain-specific geomorphic distinctions. We further show that domain-specific fine-tuning is critical for generalizable geospatial discovery in planetary settings. Our code is available at https://github.com/ml-stat-Sustech/MarsRetrieval

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 34 of its 59 references that are in the map. First posted on arXiv 15 Feb 2026.

Builds on

34 of 59 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution27 May
  2. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensing24 Nov

Other references · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Visual Instruction Tuningcited by 7,869
  3. 2025Qwen2.5-VL Technical Reportcited by 5,587
  4. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  5. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  6. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  7. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  8. 2025DINOv3cited by 1,414
  9. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  10. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,188
  11. 2023DataComp: In search of the next generation of multimodal datasetscited by 644
  12. 2024The Faiss librarycited by 376
20 more
  1. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 326
  2. 2023Data Filtering Networkscited by 250
  3. 2026Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Rankingcited by 230
  4. 2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learningcited by 173
  5. 2024GME: Improving Universal Multimodal Retrieval by Multimodal LLMscited by 170
  6. 2024E5-V: Universal Embeddings with Multimodal Large Language Modelscited by 126
  7. 2025VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documentscited by 116
  8. 2024Multimodal Autoregressive Pre-training of Large Vision Encoderscited by 109
  9. 2024MegaPairs: Massive Data Synthesis For Universal Multimodal Retrievalcited by 84
  10. 2025jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrievalcited by 76
  11. 2024ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Areacited by 71
  12. 2025Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Miningcited by 28
  13. 2025Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibratorcited by 20
  14. 2025GTR-CoT: Graph Traversal as Visual Chain of Thought for Molecular Structure Recognitioncited by 8
  15. 2025Mars-Bench: A Benchmark for Evaluating Foundation Models for Mars Science Taskscited by 5
  16. 2022MLNav: Learning to Safely Navigate on Martian Terrainscited by 3
  17. 2023ConeQuest: A Benchmark for Cone Segmentation on Marscited by 3
  18. 2024MarsSeg: Mars Surface Semantic Segmentation with Multi-level Extractor and Connectorcited by 2
  19. 2023Mapping "Brain Terrain" Regions on Mars using Deep Learningcited by 1
  20. 2026Natural Language-Driven Global Mapping of Martian Landformscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization
  2. 2025GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding
  3. 2026OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks
  4. 2026LLaVA-LE: Large Language-and-Vision Assistant for Lunar Exploration
  5. 2026LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning
  6. 2025VLM2GeoVec: Toward Universal Multimodal Embeddings for Remote Sensing
  7. 2024Towards Vision-Language Geo-Foundation Model: A Survey
  8. 2026TerraMARS: A Domain-Adapted Small-Language-Model Pipeline for Mars Terraforming Literature