mlsanityData to 14 Oct 2026

Knowledge-Augmented Vision Language Models for Underwater Bioacoustic Spectrogram Analysis

arXiv 2509.05703 ↗First posted 6 Sep 2025cs.CV cs.AI cs.IRcited by 0

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

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.

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.

Builds on

5 of 14 references.

References · 5

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  3. 2024CRAG -- Comprehensive RAG Benchmarkcited by 97
  4. 2024NatureLM-audio: an Audio-Language Foundation Model for Bioacousticscited by 33
  5. 2024Vision Language Models Are Few-Shot Audio Spectrogram Classifierscited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Seeing isn't Hearing: Benchmarking Vision Language Models at Interpreting Spectrograms
  2. 2025Advancing Marine Bioacoustics with Deep Generative Models: A Hybrid Augmentation Strategy for Southern Resident Killer Whale Detection
  3. 2025MarineEval: Assessing the Marine Intelligence of Vision-Language Models
  4. 2025Synthetic data enables context-aware bioacoustic sound event detection
  5. 2025Perch 2.0: The Bittern Lesson for Bioacoustics
  6. 2025UWBench: A Comprehensive Vision-Language Benchmark for Underwater Understanding
  7. 2025FishNet++: Analyzing the capabilities of Multimodal Large Language Models in marine biology
  8. 2024VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images