Aionic Labs is building OpenTSLM, an open-source family of time-series language models that interpret operational metrics such as sensor readings and supply-demand signals alongside context like maintenance records and market news, avoiding the token cost of serializing long histories as text or images. The models are now available through Amazon SageMaker JumpStart, with a public ARFBench example for developers to evaluate before applying them to their own domains.
Aionic Labs
Research organization developing temporal foundation models including OpenTSLM and TimeNet.
Curated Intelligence
AWS Machine Learning BlogT1·Open Source
62 pts
Hacker News AIT2·Open Source
62 pts
TimeNet is an open-source data infrastructure project for temporal foundation models that unifies incompatible time-series dataset layouts under a single storage format, TimeF, and one API for finding, building, downloading and loading data. It deliberately leaves training, inference and evaluation to the user's framework of choice. Backed by researchers from Aionic Labs, Stanford, ETH Zurich, Google and others, it is a pre-release whose public API and TimeF format may change before 1.0.