🚀 Excited to announce the AI for Tabular Data workshop at EurIPS 2025 in Copenhagen!

CfP: sites.google.com/view/eurips2... (papers due 20 Oct)

Join us @euripsconf.bsky.social to discuss neural tabular models and systems for predictive ML, tabular reasoning and retrieval, table synthesis and more ✨

Excited to share the new monthly Table Representation Learning (TRL) Seminar under the ELLIS Amsterdam TRL research theme! To recur every 2nd Friday.

Who: Marine Le Morvan, Inria (in-person)
When: Friday 11 April 4-5pm (+drinks)
Where: L3.36 Lab42 Science Park / Zoom

trl-lab.github.io/trl-seminar/

Great discussions on topics across predictive ML, LLMs for tabular data tasks, NL interfaces to tabular data 👀.

Missed it? No worries!

Papers: table-representation-learning.github.io
Talks (TBC): slideslive.com/neurips-2024
Poster pitches at: www.youtube.com/playlist?lis...

Many thanks for the very inspiring keynotes by @gaelvaroquaux.bsky.social, Yasemin Altun, Matei Zaharia, and @jpgard.bsky.social. To all authors for presenting the latest and greatest TRL research, and the panelists for bringing many insights from startups in this space! ✨

We’ve had a wonderful edition of the Table Representation Learning workshop @NeurIPS 2024! Thanks to all for bringing such great energy and contributions!

This was the 3rd edition and it's so great to see the interest in ML for tables, as well as the diversity and quality of TRL research rising 🚀.

No better way to start the day than with some quiet beautiful views of Canadian nature, before jumping into NeurIPS vibes ✨

Can't wait to appear in "The Story of AI" neurips.cc/Conferences/... 🙃

OK, off to NeurIPS for the 3rd Table Representation Learning workshop 🤩 table-representation-learning.github.io 14 Dec 8:30AM!

Will also present the TARGET benchmark for table retrieval target-benchmark.github.io 🎯!

DM for ☕!

In the middle of the AI buzz in Zürich... I really enjoyed my visit to ETH to talk about Table Representation Learning and Data Systems, and meet the excellent Systems Group!

Thanks to Ana and Gustavo for hosting me so wonderfully! 🙏

🖇️ www.madelonhulsebos.com/assets/eth_c...

Bottom line:

TARGET is the result of a great collaboration at UC Berkeley with Xingyu (Carl) Ji and @adityagp.bsky.social and is still WIP so stay tuned for more analyses & integrated evals!

Our paper will be presented at the Table Representation Learning workshop @NeurIPS 2024 ✨

Our analysis (openreview.net/pdf?id=gGGvn...) shows that:
1) out-of-the-box table embeddings far outperform BM25 which is less effective than for text retrieval,
2) retrievers are sensitive to table metadata (eg table titles),
3) there’s a stark variation of performance across datasets and tasks.