arXiv cs.AI· Nathaniel Chen, Kouroche Bouchiat, Peter Steiner, Andrew Rothstein, David Smith, Max Austin, Mike van Zeeland, Marie Roch, Azarakhsh Jalalvand, Egemen Kolemen·· 14 小时前AI 评分30
TokEye：无需参考样本的通用时频相干模式提取器
A general extractor for coherent patterns across time-frequency measurements
AI 导读
TokEye 是一种无需参考样本的方法，可从异构融合测量中学习相干结构的通用判据，且无需重新训练即可迁移到其他领域。该模型在恒星器信号上回收 82.5% 的专家标注信号，检测到 78% 的海豚哨声，并在六个基准上以 81.5% 的平均精度识别雷达事件，在 GPU 上处理完整实验频谱图耗时不到一秒。
正文 · 原文
Abstract:Scientific discovery increasingly depends on finding meaningful patterns within volumes of sensor data too large for manual inspection. Existing time-frequency event extractors are often engineered or trained on manually labeled examples for each instrument, which can be laborious and difficult to adapt to new environments. To address this, we introduce TokEye, a reference-free method that learns a general criterion for coherent structure from heterogeneous fusion measurements. A model developed under this method, without retraining, can extract signals from various other fields including marine bioacoustics and wideband radar. It recovers 82.5\% of expert-annotated stellarator signals, detects 78\% of dolphin whistles, and identifies radar events with 81.5\% average precision across six benchmarks, while processing full experimental spectrograms in under one second on a GPU. This transfer across unrelated sensors and physical systems reveals common exploitable structure in time-frequency measurements and establishes a scalable foundation for automated scientific signal discovery.
| Subjects: | Signal Processing (eess.SP); Artificial Intelligence (cs.AI); Plasma Physics (physics.plasm-ph) |
| Cite as: | arXiv:2602.20317 [eess.SP] |
| (or arXiv:2602.20317v3 [eess.SP] for this version) | |
| https://doi.org/10.48550/arXiv.2602.20317 arXiv-issued DOI via DataCite |
Submission history
From: Nathaniel Chen [view email]
[v1]
Mon, 23 Feb 2026 20:03:10 UTC (8,811 KB)
[v2]
Thu, 26 Feb 2026 01:13:38 UTC (8,811 KB)
[v3]
Tue, 27 Oct 2026 22:14:47 UTC (30,925 KB)
来源：arXiv cs.AI · arxiv.org