# Smart Eyes for Silent Threats: VLMs and In-Context Learning for THz Imaging

arXiv: https://arxiv.org/abs/2507.15576 · HTML: https://mlsanity.com/paper/2507.15576/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 15 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Builds on (most cited first, 5 of 5)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [In-context learning enables multimodal large language models to classify cancer pathology images](https://mlsanity.com/paper/2403.07407/) (2024)
- [Few-shot Learning for Domain-specific Fine-grained Image Classification](https://mlsanity.com/paper/1907.09647/) (2019)
- [Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration](https://mlsanity.com/paper/2406.07435/) (2024)

## Built on by (most cited first, 2 of 2)

- [Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images](https://mlsanity.com/paper/2606.00872/) (2026)
- [Failure or Drift? Evaluating Monocular SLAM under Synthetic and Real-World Corruptions](https://mlsanity.com/paper/2608.30690/) (2026)

## Abstract (arXiv)

Terahertz (THz) imaging enables non-invasive analysis for applications such as security screening and material classification, but effective image classification remains challenging due to limited annotations, low resolution, and visual ambiguity. We introduce In-Context Learning (ICL) with Vision-Language Models (VLMs) as a flexible, interpretable alternative that requires no fine-tuning. Using a modality-aligned prompting framework, we adapt two open-weight VLMs to the THz domain and evaluate them under zero-shot and one-shot settings. Our results show that ICL improves classification and interpretability in low-data regimes. This is the first application of ICL-enhanced VLMs to THz imaging, offering a promising direction for resource-constrained scientific domains. Code: hrefhttps://github.com/Nicolas-Poggi/ProjectTHzClassification/tree/mainGitHub repository.