Numerous research, INCLUDING the OpenTSLM paper has PROVEN they are NOT able to do this out of the box. Did you even check out the results at all? They literally compare OpenTSLM against standard text only baselines. Gemma3-270M performs better than GPT-4o using tokenized time series alone. Thus, I guess you guys are being ironic.
Sure! There is more after the 1D conv, another transformer architecture that encodes further features of the time series. The LLM can then basically query this encoder for information, also able to capture more subtle patterns. In away it's similiar to how some vision language models work.
The full paper is on the website. The arxive release of the exact same paper is pending. Click the button "read the white paper" to get the full paper.
I think you missed the point. Would you call an image analysis library to describe an image or reason over a sequence of images? Check out some of the plots in the paper to see what these models can do.
OpenTSLM models are exactly made to capture these subtle signals.
That was one of the original motivations. The model integrates the raw time series data via cross attention, with concrete time series representations learned by a raw time series encoder.