Frank Hutter (@FrankRHutter) / X

Frank Hutter

607 posts

Frank Hutter

@FrankRHutter

Founder of @Prior_Labs, Prof of #machinelearning at ELLIS Institute Tübingen & Uni Freiburg, 3x ERC Grant holder, EurAI & ELLIS fellow. All opinions are my own.

Freiburg im Breisgau, Germany

ml.informatik.uni-freiburg.de/profile/hutter/

Joined July 2018

Following

6,853

Followers

Pinned
Frank Hutter
@FrankRHutter
Dec 1, 2025
The tabular data science revolution is really here now! I’m thrilled to introduce *TabPFN Scaling Mode*, removing TabPFN’s previous limit on dataset size. The plot below shows scaling results for the biggest dataset we have tried so far (subsamples of 100k and 1M, and the full
9.3K
Frank Hutter
@FrankRHutter
Oct 21, 2022
This may revolutionize data science: we introduce TabPFN, a new tabular data classification method that takes 1 second & yields SOTA performance (better than hyperparameter-optimized gradient boosting in 1h). Current limits: up to 1k data points, 100 features, 10 classes. 🧵1/6
Frank Hutter
@FrankRHutter
Jan 8, 2025
The data science revolution is getting closer. TabPFN v2 is published in Nature: nature.com/articles/s4158… On tabular classification with up to 10k data points & 500 features, in 2.8s TabPFN on average outperforms all other methods, even when tuning them for up to 4 hours🧵1/19
264K
Frank Hutter
@FrankRHutter
Mar 17, 2022
I’m thrilled to announce that I’ve been awarded an #ERC Consolidator Grant. 2 million Euros to work on what I call „Deep Learning 2.0“. I hope that the next generation of DL can achieve Trustworthy AI by design. Details about DL 2.0 in this blog post: automl.org/deep-learning-… 1/3
Frank Hutter
@FrankRHutter
Jan 28, 2022
Hooray, we got 5/5 submissions accepted at #ICLR2022. Congratulations to all my wonderful students and collaborators. A brief overview of our papers below:
Frank Hutter
@FrankRHutter
Nov 18, 2023
I like this new paper on DL vs trees at the #NeurIPS 2023 datasets and benchmark track: arxiv.org/abs/2305.02997. One of their findings: #TabPFN performs well across 98 datasets: it ties for 1st place with CatBoost in predictive performance but is 200x faster to train. This is
Frank Hutter
@FrankRHutter
Nov 28, 2022
Time for an update on experiments with our learned TabPFN: we performed a much more comprehensive analysis on 179 datasets, confirming the patterns from our previous evaluation on 30 datasets and looking in much more detail. A long thread with lots of plots🧵1/17
92K
Frank Hutter
@FrankRHutter
Jan 13, 2025
#TabPFN v2 also excels on time series! Just before our Nature paper came out, we had this paper at the #NeurIPS time series workshop: openreview.net/forum?id=ho8Yx… We simply cast time series as tabular regression and use exactly the model from Nature. It’s crazy that this works! 🧵1/10
29K
Frank Hutter
@FrankRHutter
Feb 3, 2021
I like this post and would advise all PhD students to follow it! In a dynamic field like machine learning, life always keeps on getting busier (even once you have a tenured position and brilliant PhD students to keep up with ;-) and you need to schedule breaks to recharge!
Not so Exhausted Anymore, Ph.D.
@PhdExhausted
Jan 21, 2021
I'll relax once I submit this paper. I'll relax once I submit my thesis. I'll relax once I defend my thesis. I'll relax after I get a post-doc. Damn! I guess I'll have to relax after I get a permanent position. No. The future always gets busier. Schedule proper breaks NOW. 💛
Frank Hutter
@FrankRHutter
Feb 5, 2025
I‘m excited to announce that we raised €9m in a pre-seed round for @prior_labs, the world’s first company focussed on building tabular foundation models! The round was led by @balderton, with participation from @xtxmarkets, Hector Foundation, Atlantic Labs, and Galion.exe. We’re
23K
Frank Hutter
@FrankRHutter
Oct 21, 2022
Replying to @FrankRHutter
TabPFN is radically different from previous ML methods. It is meta-learned to approximate Bayesian inference with a prior based on principles of causality and simplicity. Here‘s a qualitative comparison to some sklearn classifiers, showing very smooth uncertainty estimates. 2/6
Frank Hutter
@FrankRHutter
Oct 21, 2022
Replying to @FrankRHutter
Please see our blog post automl.org/tabpfn-a-trans… for details & code. Also, we just got an oral at the #NeurIPS table representation learning workshop …ble-representation-learning.github.io 🎉Joint work with my outstanding students @noahholl, @SamuelMullr and @KEggensperger. 6/6
Frank Hutter
@FrankRHutter
Oct 25, 2022
Thanks for the many comments on my tweet on TabPFNs: x.com/FrankRHutter/s… Here's an update on how this may revolutionize data science. TL;DR: learning classification algorithms rather than programming them; real-time AutoML; democratizing ML to tackle *small data*! 🧵1/9
Frank Hutter
@FrankRHutter
Oct 21, 2022
This may revolutionize data science: we introduce TabPFN, a new tabular data classification method that takes 1 second & yields SOTA performance (better than hyperparameter-optimized gradient boosting in 1h). Current limits: up to 1k data points, 100 features, 10 classes. 🧵1/6
Frank Hutter
@FrankRHutter
Dec 3, 2021
Exciting news: following a series of 8 AutoML workshops at ICML, we will hold the 1st International Conference on AutoML in 2022. Co-located with ICML, 3 days, currently planned in person. Website: automl.cc Submission deadline: Feb 24, 2022 #AutoML #AutoML_Conf 1/
Frank Hutter
@FrankRHutter
Oct 21, 2022
Replying to @FrankRHutter
If you'd like to play with TabPFNs yourself, here is a direct link to the Colab with a scikit-learn like interface:
colab.research.google.com
TabPFNDemo
Colaboratory notebook