onasta
Re:Show HN: TabPFN-3.5, a Tabular Foundation Model for messy real-worl...
on Tuesday September 15, 2026 @12:56PM (#49715385)
I'm excited to announce the release of our new Tabular Foundation Model TabPFN-3.5!
It improves a lot on standard tabular prediction problems (rank 1 by far [TabArena](https://github.com/autogluon/tabarena) and much faster than the competing models, 98% win rate against a well tuned XGBoost). But most importantly it really improves on the messy real-world data we've seen across industries. Be it non-i.i.d. data with temporal or grouped splits, tables with strings, text and images, high-cardinality categorical features, or wide tables with many features, we're also state of the art. Inside our harness, it's also the best model to predict on relational data, outperforming specific graph-based models.
Would love to hear how it performs on your own data!
Show HN: RelArena-α – open-source releases for Relational Learning
https://github.com/PriorLabs/relarena
I’m happy to announce our first release in relational learning at Prior Labs, continuing our commitment to open science.Most of the data that actually matters to a business- users, transactions, sessions, orders- lives in relational databases, not in a single spreadsheet. SQL is built for backward-looking analysis: what happened, how much, when. It can't tell you whether a given user will churn...
TabPFN-3: scaling foundation models for tabular data to 1M rows
Show HN: TabPFN Scaling Mode – Tabular Foundation Model on millions of rows
https://priorlabs.ai/technical-reports/large-data-model
I’m excited to announce Scaling Mode for TabPFN-2.5, our tabular foundation model (Large Tabular Model). This removes any fixed upper limits on dataset sizes and extends TabPFN to datasets with millions of rows.What is Scaling Mode? A new pipeline around TabPFN-2.5 designed for large-N workloads, which removes the fixed row limit of TabPFN. The system works with large training sets, constrained...
Show HN: TabPFN-2.5 – SOTA foundation model for tabular data
https://priorlabs.ai/technical-reports/tabpfn-2-5-model-report
I am excited to announce the release of TabPFN-2.5, our tabular foundation model that now scales to datasets of up to 50,000 samples and 2,000 features - a 5x increase from TabPFN v2, published in the Nature journal earlier this year. TabPFN-2.5 delivers state-of-the-art predictions in one forward pass without hyperparameter tuning across classification and regression tasks.What’s new in...
Re:Show HN: TabPFN v2 – A SOTA foundation model for small tabular data
on Thursday January 09, 2025 @06:30PM (#42650930)
There have been a ton of improvements! Much better performance overall, way larger data size limit (1K-->10K rows, 100-->500 features), regression support, native categorical data and missing values handling, much better support for uninformative or outlier features etc.
Re:Show HN: TabPFN v2 – A SOTA foundation model for small tabular data
on Thursday January 09, 2025 @05:55PM (#42650700)
TabPFN is better on numerical data since v1 (see figure 6 in the CARTE paper). CARTE's main strength in on text features, which are now also supported for TabPFN v2 API version (https://github.com/PriorLabs/tabpfn-client). We compared this to CARTE and found our model to be generally quite better, and much faster. CARTE multi-table approach is also very interesting, and we want to tackle this setting in the future.
Show HN: TabPFN v2 – A SOTA foundation model for small tabular data
https://www.nature.com/articles/s41586-024-08328-6/link
I am excited to announce the release of TabPFN v2, a tabular foundation model that delivers state-of-the-art predictions on small datasets in just 2.8 seconds for classification and 4.8 seconds for regression compared to strong baselines tuned for 4 hours. Published in Nature, this model outperforms traditional methods on datasets with up to 10,000 samples and 500 features.The model is...
Re:Why do tree-based models still outperform deep learning on tabular ...
on Thursday August 04, 2022 @05:20PM (#32348430)
Super interesting! Do you know the kind of data that it's usually used for? And in the remaining 80% to 60%, do NNs acccount for a large portion of the best models?
Bonus question: are the stats you're mentioning publically available?