arXiv:2607. 07758v1 Announce Type: new Abstract: Foundation models (FMs) have transformed machine learning from isolated task-specific model development toward general-purpose models pretrained on broad data and adapted to multiple downstream tasks.
By Syed Usama Imtiaz, Mitra Nasr Azadani, Nasrin Alamdari
arXiv:2609.26214v1 Announce Type: new
Abstract: We present a methodology that places a 3D digital twin (DT) of the environment as the main enabler behind the development of radio sensing at scale. Th...
By \'Eloi Sainte-Beuve (Orange Research), Guillaume Larue (Orange Research), Louis-Adrien Dufr\`ene (Orange Research), Quentin Lampin (Orange Research), Ali Al Khansa (Orange Research)
arXiv:2606. 20291v1 Announce Type: new Abstract: Remote sensing is increasingly relied upon to deliver actionable science for forest and wildfire risk management across large landscapes.
By Luke J. Zachmann, David D. Diaz, Vincent A. Landau, Chelsey Walden-Schreiner, Tony Chang, Nathan E. Rutenbeck, Katharyn A. Duffy, Kiarie Ndegwa, Andreas Gros, Scott Conway, Guy Bayes
arXiv:2608.23746v1 Announce Type: new
Abstract: State space models, especially Visual State Space Duality (VSSD), have emerged as efficient linear-time alternatives to Transformers for dense visual t...
By Kangning Wang, Haopeng Zhang, Zhiguo Jiang
The computational complexity of Transformers scales quadratically with the number of tokens, which significantly constrains the efficiency of vision models, particularly recent ViT-based foundation models in dense prediction tasks. Instance segmentation, a typical dense visual prediction task in the remote sensing field, faces similar challenges.
The paper demonstrates that Earth observation (EO) models can be automatically constructed and refined by a general-purpose coding agent when provided with a harness (defining permissible tools) and a verifier (defining success criteria). By casting any verifiable EO task—using labeled benchmarks, independent sensors, physical models, or repeated observations—as such a harness-verifier pair, the agent recursively improves its own outputs. On four EO benchmarks covering optical, SAR, and multispectral time-series imagery, the agent-built models outperform state‑of‑the‑art methods while retaining most accuracy with only about 1 % of the training labels.