News for hackers. Stuff that matters.

A comment on Google's 200M-parameter time-series foundation model with 16k context.

Re:Google's 200M-parameter time-series foundation model with... by Foobar8568 on Tuesday March 31, 2026 @01:36AM (#47583129)
Somehow I missed that one. Are there any competition on this?

I always had difficulties with ML and time series, I'll need to try that out.

[ Parent | on HN ]
Re:Google's 200M-parameter time-series foundation model with... by rockwotj on Tuesday March 31, 2026 @02:00AM (#47583289)
https://www.datadoghq.com/blog/datadog-time-series-foundatio...

https://moment-timeseries-foundation-model.github.io/

https://arxiv.org/abs/2403.07815

A friend at work used one to predict when our CEO would post in Slack, which is verry entertaining to see if correct.

[ Parent | on HN ]
Re:Google's 200M-parameter time-series foundation model with... by Foobar8568 on Tuesday March 31, 2026 @07:57AM (#47586068)
Many thanks for the links!
[ Parent | on HN ]
Re:Google's 200M-parameter time-series foundation model with... by chwzr on Tuesday March 31, 2026 @04:46AM (#47584437)
there is TabPFN [1] which also has time series capabilities.

[1] https://priorlabs.ai/tabpfn

[ Parent | on HN ]
Re:Google's 200M-parameter time-series foundation model with... by _1 on Tuesday March 31, 2026 @08:57AM (#47586705)
https://www.opentslm.com/
[ Parent | on HN ]
Re:Google's 200M-parameter time-series foundation model with... by bitshiftfaced on Tuesday March 31, 2026 @09:06AM (#47586792)
There are some other transformer based models on the GIFT leaderboard: https://huggingface.co/spaces/Salesforce/GIFT-Eval
[ Parent | on HN ]