# Beyond Templates: Revisiting Zero-Shot Remote Sensing through Meta-Prompting

arXiv: https://arxiv.org/abs/2606.20702 · HTML: https://mlsanity.com/paper/2606.20702/

## 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 19 of its 28 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification](https://mlsanity.com/paper/1608.05167/) (2016)
- [Demystifying CLIP Data](https://mlsanity.com/paper/2309.16671/) (2023)
- [Exploring Models and Data for Remote Sensing Image Caption Generation](https://mlsanity.com/paper/1712.07835/) (2017)
- [RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2306.11300/) (2023)
- [SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing](https://mlsanity.com/paper/2312.12856/) (2023)
- [PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval](https://mlsanity.com/paper/1706.03424/) (2017)
- [MLRSNet: A Multi-label High Spatial Resolution Remote Sensing Dataset for Semantic Scene Understanding](https://mlsanity.com/paper/2010.00243/) (2020)
- [The Double-Ellipsoid Geometry of CLIP](https://mlsanity.com/paper/2411.14517/) (2024)
- [Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs](https://mlsanity.com/paper/2403.11755/) (2024)
- [Whitened CLIP as a Likelihood Surrogate of Images and Captions](https://mlsanity.com/paper/2505.06934/) (2025)

## Abstract (arXiv)

Vision-language models (VLMs) have sparked growing interest in zero-shot Earth Observation (EO) downstream tasks, with further gains enabled by remote-sensing-adapted models. We examine this setting across 17 VLM variants and 12 remote sensing (RS) datasets under Meta-Prompting for Visual Recognition (MPVR), and show that zero-shot performance remains highly sensitive to textual design choices, from the meta-prompts used to guide the LLM in generating class descriptions to the descriptions themselves. We explore why semantically rich LLM-generated class descriptions do not translate into consistent gains over simple domain-adapted CLIP-style descriptions. While LLM descriptions are more semantically expressive, they can also introduce noise in the text embedding space, reducing robustness in downstream tasks. We support this observation through a text log-likelihood analysis in the whitened CLIP feature space, comparing LLM-generated and template-based descriptions. Building on this finding, we study query embedding calibration and show that lightweight calibration of the query space consistently yields strong improvements in zero-shot classification and retrieval. Overall, our results provide practical insight into the trade-off between semantic richness and robustness, and identify embedding calibration as a simple and effective tool for improving zero-shot remote sensing performance.