Generalist Vision-Language Models for Fast Radio Burst detection: a zero-shot benchmark against a specialized detector
Raiff H. Santos, Amilcar R. Queiroz, Tharcisyo S. S. Duarte, K. E. L. de Farias, Rafael A. Batista
cs.LG, astro-ph.HE, astro-ph.IM
Submitted: 2026-08-20
Updated: 2026-08-21
Comments: 24 pages, 4 figures
Code: https://github.com/expnn/SwinYNet
License: http://creativecommons.org/licenses/by/4.0/
The gist: Fast Radio Bursts (FRBs) are millisecond-duration radio transients whose automated detection increasingly relies on highly specialized deep learning models.
Terminology
Abstract
Fast Radio Bursts (FRBs) are millisecond-duration radio transients whose automated detection increasingly relies on highly specialized deep learning models. These detectors achieve exceptional performance, but they require large task-specific training datasets and cannot be redefined without retraining. In this work, we evaluate whether small, open-weight, locally run generalist Vision-Language Models (VLMs) can detect FRBs in dynamic spectra under a zero-shot, prompt-only regime, with no fine-tuning and no labeled examples, returning structured decisions with a natural-language justification. From a controlled set of 3000 simulated L-band dynamic spectra containing FRBs, structured Radio Frequency Interference (RFI), and noise, we draw a balanced binary benchmark of 2000 samples and compare two such VLMs (Gemma 4 2B and 4B), sample by sample, against the state-of-the-art specialized detector SwinYNet. At the default threshold, Gemma 4 2B reaches an accuracy of 93.65%, with no statistically significant difference from SwinYNet (92.90%), while showing a significantly lower false-positive rate on structured RFI (6.4% vs. 25.0%) and no false positives on pure noise. SwinYNet retains a perfect probabilistic ranking on this benchmark (ROC-AUC of 1.0000 vs. 0.9482), a ceiling that the zero-shot VLM approaches from general-purpose pretraining alone. Rewriting the prompt alone reconfigures the same models for three-class FRB/RFI/noise classification on the full set of 3000 spectra, where they reach up to 86% accuracy without a single false FRB.
Sources
- Do Vision-Language Models See Dwarf Galaxies the Way We Do?
- AstroLLaVA: towards the unification of astronomical data and natural language
- Talking with the Latents -- how to convert your LLM into an astronomer
- Gemini: A Family of Highly Capable Multimodal Models
- Radio Astronomy in the Era of Vision-Language Models: Prompt Sensitivity and Adaptation
- NE2001.I. A New Model for the Galactic Distribution of Free Electrons and its Fluctuations
- A systematic evaluation of vision-language models for observational astronomical reasoning tasks
- AstroAlertBench: Evaluating the Accuracy, Reasoning, and Honesty of Multimodal LLMs in Astronomical Classification
- AstroMMBench: A Benchmark for Evaluating Multimodal Large Language Models Capabilities in Astronomy
- Gemma: Open Models Based on Gemini Research and Technology
- Ablation Studies in Artificial Neural Networks
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks