# Knowledge-Augmented Vision Language Models for Underwater Bioacoustic Spectrogram Analysis

arXiv: https://arxiv.org/abs/2509.05703 · HTML: https://mlsanity.com/paper/2509.05703/

## 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 5 of its 14 references that are in the map.
- First posted on arXiv 6 Sep 2025.

## 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, 5 of 5)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [CRAG -- Comprehensive RAG Benchmark](https://mlsanity.com/paper/2406.04744/) (2024)
- [NatureLM-audio: an Audio-Language Foundation Model for Bioacoustics](https://mlsanity.com/paper/2411.07186/) (2024)
- [Vision Language Models Are Few-Shot Audio Spectrogram Classifiers](https://mlsanity.com/paper/2411.12058/) (2024)

## Abstract (arXiv)

Marine mammal vocalization analysis depends on interpreting bioacoustic spectrograms. Vision Language Models (VLMs) are not trained on these domain-specific visualizations. We investigate whether VLMs can extract meaningful patterns from spectrograms visually. Our framework integrates VLM interpretation with LLM-based validation to build domain knowledge. This enables adaptation to acoustic data without manual annotation or model retraining.