AI RESEARCH
TS-Haystack: A Multi-Scale Retrieval Benchmark for Time Series Language Models
arXiv CS.LG
•
ArXi:2602.14200v3 Announce Type: replace Time Series Language Models (TSLMs) are emerging as unified models for reasoning over continuous signals in natural language. However, long-context retrieval remains a major limitation: existing models are typically trained and evaluated on short sequences, while real-world time-series sensor streams can span millions of datapoints. This mismatch requires precise temporal localization under strict computational constraints, a regime that is not captured by current benchmarks. We