Zero-shot Gemma 4 VLMs achieve 93.65% accuracy on simulated FRB detection, statistically indistinguishable from the specialized SwinYNet detector at the default threshold, while rejecting structured RFI significantly better.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generalist Vision-Language Models for Fast Radio Burst detection: a zero-shot benchmark against a specialized detector
Zero-shot Gemma 4 VLMs achieve 93.65% accuracy on simulated FRB detection, statistically indistinguishable from the specialized SwinYNet detector at the default threshold, while rejecting structured RFI significantly better.