Chronos-2: From Univariate to Universal Forecasting · HackerPapers discussions

Chronos-2: From Univariate to Universal Forecasting — mentioned by ChernovAndrei

Wed, 24 Dec 2025 13:14:38 GMT

There is no single answer, because there are multiple architectures for foundation time-series models, such as T5, decoder-only models, and state-space models (SSMs). For Chronos-2 (the current state of the art in time-series modeling), the setup is almost identical to that of LLMs because it is based on the T5 architecture. The main difference is that, in time-series models, tokens correspond to subintervals in the real-valued (ℝ) space. You can check the details here: https://arxiv.org/pdf/2510.15821

Paper and discussion history. A mention is not an endorsement.

Chronos-2: From Univariate to Universal Forecasting — mentioned by armcat

Tue, 23 Dec 2025 07:16:35 GMT

The promise is similar to LLMs, if you pretrain on sufficiently large timeseries datasets with sufficiently large variance/characteristics, that you will be able to transfer the model to a completely different use case that exhibits somewhat similar characteristics (in latent space). But it’s always good to check what kind of data the model was trained on, eg Chronos 2.0 training data is described in Appendix A Table 6 here: https://arxiv.org/pdf/2510.15821

Paper and discussion history. A mention is not an endorsement.