{"ID":6138249,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-11T13:15:01.920489011Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.07382","arxiv_id":"2607.07382","title":"Generalist Vision-Language Models for Fast Radio Burst detection: a zero-shot benchmark against a specialized detector","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.","short_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, w...","url_abs":"https://arxiv.org/abs/2607.07382","url_pdf":"https://arxiv.org/pdf/2607.07382v1","authors":"[\"Raiff H. Santos\",\"Amilcar R. Queiroz\",\"Tharcisyo S. S. Duarte\",\"K. E. L. de Farias\",\"Rafael A. Batista\"]","published":"2026-07-08T13:15:29Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"astro-ph.HE\",\"astro-ph.IM\"]","methods":"[\"Language Model\"]","has_code":false}