Tabular Foundation Models

# Reading Group: Tabular Foundation Models

Join us at our next meetup where we'll be exploring the emerging field of tabular foundation models. While much attention in AI has focused on text, images, and video, the vast majority of real-world data exists in tables. These new foundation models aim to do for tabular data what transformers did for natural language—creating powerful, generalizable systems pre-trained on diverse datasets.

We'll be focusing on a recent paper that proposes a breakthrough approach to tabular machine learning:
**Paper**: "TabPFN - One Model to Rule Them All?"
**Link**: https://arxiv.org/abs/2505.20003
**Podcast about the topic**: https://www.superdatascience.com/podcast/863
**Github**: https://github.com/PriorLabs/TabPFN

This session will examine how these models can learn patterns across diverse tabular structures, potentially revolutionizing how we approach tasks like classification and regression on spreadsheet-like data.

Please try to look at some of the material before attending. And, even better, have a go at using TabPFN on tabular data. These discussions are most valuable when participants have spent time exploring the topic beforehand. The goal is for us all to meet and learn from each other's insights and questions.

## Who is this meeting for?
Anyone interested in Data Science and Machine Learning. We aim to have the discussion at an intermediate to advanced level, but we welcome people of all levels.

## Discussion Format:
Similar to a reading group where we give everyone a chance to share what they have learned and ask questions about where they got stuck. Those who did not look at materials beforehand or would just like to listen are welcome to pass their turn.

## Meeting Schedule:
- 6:00 - 6:30: Arrive / informal chat
- 6:30 - 6:35: Introductions
- 6:35 - 7:25: Discussion
- 7:25 - 7:30: Nominate and vote for the next meeting's topic
- 7:30: Meeting ends

We hope to see you there!