arXiv Computer Vision September 7, 2026 By Mohanad Albughdadi

MEOX: Compact Multimodal Mixture-of-Experts for Earth Observation

Read the original on arXiv Computer Vision →

MEOX is a compact multimodal masked autoencoder designed for Earth Observation that uses a 2.939 million‑parameter encoder and 3.115 million total parameters. It incorporates sensor‑specific adapters, explicit validity signals, and a shared sparse‑expert block to maintain modality‑dependent processing before a learned patch‑wise fusion, followed by fourteen encoder blocks that process a single spatial sequence with four metadata tokens. Pretrained on 1.228 million MMEarth64 samples, MEOX achieves strong performance on GEO‑Bench tasks, surpassing prior CSMoE results, and demonstrates effective sensor‑flexible representation learning with a modest parameter budget.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Jun 10

Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks

arXiv:2606. 10819v1 Announce Type: cross Abstract: RS-MLLMs enable natural-language understanding and spatial reasoning over earth observation imagery.

By Miaoxin Cai, Guanqun Wang, Wei Zhang, Guangyao Zhou, Yin Zhuang, Tong Zhang, Hao Wang, He Chen, Jun Li

llms multimodal benchmarks safety

arXiv Computer Vision

Oct 26

LoCA: Enabling Multi-Modality in Geospatial Location Encoders

arXiv:2610.32894v1 Announce Type: new Abstract: Location encoders map geographic coordinates to high-dimensional descriptors through contrastive alignment with paired Earth Observation imagery. We pr...

By Panagiotis Koromilas, Eleanna Vali, Diogenis Antonopoulos, Eleni Saka, Dimitris Christofis, Nikolaos Ioannis Bountos, Konstantin Klemmer, Ioannis Papoutsis, Yannis Panagakis, Mihalis A. Nicolaou

rag multimodal benchmarks safety

arXiv AI

Aug 10

SLED: Scalable Location Encoding via Distillation

arXiv:2608. 06612v1 Announce Type: cross Abstract: The plethora of readily available geospatial data offers exciting opportunities to learn high quality representations of the planet, but the sheer size of the Earth Observations (EO), differing modalities, and different sensor types pose significant challenges in doing so.

By Kevin Lane, Zhongying Wang, Esther Rolf, Morteza Karimzadeh

rag efficiency multimodal benchmarks

arXiv AI

Jun 12

Emerging Flexible Designs for Geospatial Multimodal Foundation Models

arXiv:2606. 12595v1 Announce Type: cross Abstract: Foundation models are rapidly transforming Earth observation by enabling scalable pretraining across diverse unlabeled geospatial modalities.

By Philipe Dias, Waqwoya Abebe, Abhishek Potnis, Aristeidis Tsaris, Dan Lu, Xiao Wang, Dalton Lunga

computer-vision multimodal benchmarks safety

arXiv AI

Sep 15

Multimodal-Multiresolution Foundation Model for Lunar Remote Sensing

The paper introduces a multimodal foundation model for lunar remote sensing, trained from scratch on SomBench—a dataset of nearly two million co‑registered tile bundles across 11 modalities at 1 m and 100 m resolutions. The model extends the TerraMind masked‑token architecture with lunar‑specific features such as explicit acquisition geometry and joint training of two spatial scales, and employs FlexiViT patch embeddings for adaptable patch sizes. Evaluation on crater detection, irregular mare patch segmentation, and polar ice prospectivity regression shows that the pretrained model matches or surpasses ImageNet‑pretrained baselines, with notable label efficiency and effective adaptation via LoRA.

By Paolo Fraccaro, Gabby Nyirjesy, Daniela Szwarcman, Himanshu Patil, Vishal Gaur, Rohit Lal, Rachel A. Slank, Geoffrey Dawson, Hiyam Debary, Michael K. Barker, Andrew Annex, Vishnu Viswanathan, Zachary Morse, Ethan I. Schaefer, Nikolaos Dionelis, Ankur Kumar, Campbell D. Watson, Manil Maskey, Rebekah I. Dawson-Rigas, Juan Bernab\'e-Moreno, Rahul Ramachandran, Sujit Roy

rag computer-vision fine-tuning multimodal benchmarks

arXiv Computer Vision

Sep 24

VLM2GeoVec: Toward Universal Multimodal Embeddings for Remote Sensing

The paper introduces RSMEB, a unified benchmark for remote‑sensing multimodal retrieval that evaluates both cross‑modal and interleaved retrieval across 21 tasks under a single ranking protocol. It also presents VLM2GeoVec, an instruction‑conditioned single‑encoder model that embeds image, text, bounding‑box, and geo‑coordinate tokens into one sequence and achieves state‑of‑the‑art performance on region‑caption, referring‑expression, and semantic geo‑aware retrieval while remaining competitive on conventional tasks. The authors provide code, checkpoints, and data on GitHub to facilitate reproducibility.

By Emanuel S\'anchez Aimar, Gulnaz Zhambulova, Fahad Shahbaz Khan, Yonghao Xu, Michael Felsberg

rag multimodal benchmarks

One email a morning, machine-written

Related stories

Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks

LoCA: Enabling Multi-Modality in Geospatial Location Encoders

SLED: Scalable Location Encoding via Distillation

Emerging Flexible Designs for Geospatial Multimodal Foundation Models

Multimodal-Multiresolution Foundation Model for Lunar Remote Sensing

VLM2GeoVec: Toward Universal Multimodal Embeddings for Remote Sensing