This is quite a big deal.

Most tabular ML still starts with the same assumption: new dataset, new training run. That will no more be true.

Synthefy just launched a foundation-model platform for structured numerical data where tables, transactions, sensor readings and time series should not need a separately trained model for every prediction problem.

So tabular ML can work like foundation models do elsewhere: reuse one pretrained model instead of rebuilding for every problem.

The big deal is they are trying to remove the “train a new machine-learning model for every new table/problem” step.

With @synthefyinc : New dataset → give Nori some labeled rows → ask it to predict new rows.

You pass labeled rows as context, then query it with new rows. fit() does not train or fine-tune anything. It stores the examples, and predict() produces the regression outputs in a forward pass.

Its open-source model Nori takes labeled rows as examples and predicts values for new rows with no training or fine-tuning step, with fit storing the labeled rows as context and predict returning values for new rows in a single forward pass.

And Synthefy raised $6.5M, led by Wing Venture Capital.

Nori can run locally or through a hosted API, is available under Apache 2.0, and Synthefy says it has reached almost 600K model downloads and 5,000 Python installs.

With just 30 million parameters, Nori-30M rivals Google's 1.6-billion-parameter TabFM across public regression benchmarks. With thinking enabled, Nori-30M-thinking surpasses it, achieving frontier accuracy at roughly 2% of the size.

🧵 1.