ทวีตที่ปักหมุด
📢Announcing a Call for Papers for the @icmlconf "Foundation Models for Structured Data" Workshop!
English
Nick Erickson
196 posts
Nick Erickson
@innixma
Author & Lead Developer of @AutoGluon and TabArena Research Scientist at Prior Labs #automl #tabpfn #opensource
New York, NY เข้าร่วม Aralık 2018
86 กำลังติดตาม1.2K ผู้ติดตาม
🚀 AutoGluon 1.5 is out - pushing the frontier of tabular and time series learning!
🏆New SOTA on TabArena: +60 Elo, 2x faster training, 50% faster inference, 3% lower rel error vs 1.4
🧠New Models: RealTabPFN-2.5, TabDPT, Chronos-2
⏱️AutoGluon-TimeSeries: 80% win-rate vs 1.4
English
Wow! It is amazing to see the progress being made. As I said when TabPFNv2 released: "time to code".
Frank Hutter@FrankRHutter
The data science revolution continues — TabPFN is now SOTA up to 50k data points and 2000 features 🚀 For the size limits of TabPFNv2, in a forward pass Real-TabPFN-2.5 outperforms AutoGluon 1.4 (complex ensemble including TabPFNv2 tuned for 4h) by 93 ELO points on TabArena.🧵1/
English
@HassanConor Yes, it already has been! We are collecting results for additional methods beyond those in our original preprint and will release their results together ahead of NeurIPS. Here is a preview of Mitra's results on TabPFN datasets prior to incorporating tuned and tuned + ensembling.
English
@innixma Nice! Is Mitra going to get benchmarked on TabArena soon?
English
💥 Tabular ML just got a massive upgrade.
🚀 AutoGluon 1.4.0 is here — our biggest release yet.
🔥 Extreme Preset → biggest performance leap ever
🧠 5 new SOTA models
🤖 MLZero 1.0 (zero‑code multimodal AutoML)
📊 TabArena benchmark
⚡ Time series speedups
English
⚡ Time Series
- Up to 7× faster training & inference on large datasets
- New PerStepTabular forecasting model
📌 Learn more:
🔗 Full release: github.com/autogluon/auto…
🔗 TabArena: tabarena.ai
🔗 Mitra: amazon.science/blog/mitra-mix…
🔗 MLZero: github.com/autogluon/auto…
English
🤖 MLZero 1.0 (AutoGluon Assistant)
- Zero‑code AutoML for tabular, image, text, audio
- New WebUI + MCP integration
- Multi‑agent LLM system for end‑to‑end ML automation
📊 TabArena
- Living leaderboard for tabular ML
- Continuous benchmarking feeding directly into AutoGluon
English
Foundation Models for Structured Data Workshop, Today, ICML 2025, starting at 9 AM PT, West Ballroom D, best room in the building! Let's do this!
English
Checkout the full schedule here, kicked off by an invited talk from @FrankRHutter on the path towards TabPFNv3! icml.cc/virtual/2025/w…
And checkout the workshop's website for more information: icml-structured-fm-workshop.github.io
English
Attending #icml25, eager to discuss all things tabular data, structured foundation models, and AutoML! Lots of progress has been made this year, exciting times ahead! Next AutoGluon release is very soon.
English
Nick Erickson รีทวีตแล้ว
I will talk about TabArena at the AutoML seminar this week, join me :)
More information: automl-seminars.github.io
English
Nick Erickson รีทวีตแล้ว
It's great to have this new open-source benchmark for tabular data 🚀
It's really comprehensive, created and maintained by serious open source contributors from various groups, and I expect it to quickly become the new standard benchmark.
I'm super excited that progress in the tabular space is exploding! It's also interesting to see that, for the datasets in TabPFN v2's constraints (<10k data points, <500 features), half a year after its release, TabPFN v2 still strongly outperforms all other methods!
Lennart Purucker@LennartPurucker
🚨What is SOTA on tabular data, really? We are excited to announce 𝗧𝗮𝗯𝗔𝗿𝗲𝗻𝗮, a living benchmark for machine learning on IID tabular data with: 📊 an online leaderboard (submit!) 📑 carefully curated datasets 📈 strong tree-based, deep learning, and foundation models 🧵
English
TabArena is a living benchmark. With the community, we will continually update it! Authors:
@innixma
@LennartPurucker
@atschalz
@DHolzmueller
Prateek Mutalik Desai
@_geoalgo_
@FrankRHutter
LB: tabarena.ai
Paper: arxiv.org/abs/2506.16791…: tabarena.ai/code
4/4
English
Tabular foundation models work. They achieve performance competitive with or exceeding the prior state-of-the-art within their supported dataset constraints. While more work needs to be done in overcoming these constraints, the results are very promising.
3/
English
We put all the best practices for tabular data benchmarking in one place to make TabArena, a living benchmark for tabular data. Compare with the very best implementations of state-of-the-art methods out of the box! Here are my thoughts: 🧵
Lennart Purucker@LennartPurucker
🚨What is SOTA on tabular data, really? We are excited to announce 𝗧𝗮𝗯𝗔𝗿𝗲𝗻𝗮, a living benchmark for machine learning on IID tabular data with: 📊 an online leaderboard (submit!) 📑 carefully curated datasets 📈 strong tree-based, deep learning, and foundation models 🧵
English
Nick Erickson รีทวีตแล้ว
🚨What is SOTA on tabular data, really? We are excited to announce 𝗧𝗮𝗯𝗔𝗿𝗲𝗻𝗮, a living benchmark for machine learning on IID tabular data with:
📊 an online leaderboard (submit!)
📑 carefully curated datasets
📈 strong tree-based, deep learning, and foundation models
🧵
English