snimu (Sebastian Müller)
@omouamoua
I love the RL Residency
Timeseries prediction is very important, and well-fitted for RLM and multi-agent work. This environment gives us infinite synthetic data that can be made arbitrarily easy of difficult, and is shown to transfer to real data.
Incredible work @Nzuma!
Timeseries prediction is very important, and well-fitted for RLM and multi-agent work. This environment gives us infinite synthetic data that can be made arbitrarily easy of difficult, and is shown to transfer to real data.
Incredible work @Nzuma!
nicozumarraga@nzuma0 · Oct 8Frontier Time Series Language Models struggle with precise anomaly localization over long contexts, when useful signals might be hidden in hours of recordings.
In our new paper we trained a tiny Recursive Language Model to SoTA performance on long context time series.
We
In our new paper we trained a tiny Recursive Language Model to SoTA performance on long context time series.
We
Open quoted post →
1 87