🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Wondering how humans should be involved in designing #AutoML solutions 🤔? Check out our #ICML2024 paper: "Position: A Call to Action for a Human-Centered AutoML Paradigm"! 📄✨ proceedings.mlr.press/v235/lindauer2… Drop by at our poster on Thu, Jul 25 at 11:30 AM in Hall C 4-9 #2003 📅 1/3

📝In the meantime you can also read a short summary blog post at automl.org/position-a-cal… or watch a video summary at youtube.com/watch?v=17lH-f… 🎥 2/3

Joint work with @LindauerMarius, Florian Karl, Julia Moosbauer, Alexander Tornede, Andreas Mueller, Frank Hutter and SLDS / Bernd Bischl

In #Vienna for #ICML2024 to present our latest work! With Herilalaina Rakotoarison, Steven Adriaensen, Samir, Eddie Bergman, and Frank Hutter, we introduce, ifBO: In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization.

In less than a month, the AutoML Conference 2024 will be in Paris. I don't think that we can quite compete with the #Olympics, but we will give our best ;-)

What a great pleasure it was to host the AutoML_conf here in Paris this week. Big shoutout to all co-organizers and in particular to the amazing Elena Raponi Anja Janković Simon Provost and to the online chairs Gabi Kadlecová and @AndreBiedenkapp See you in NYC next year 😃

We have another opening for a PhD in AutoML Universität München. Apply now at job-portal.lmu.de/jobposting/ba1… #PhD #MachineLearning #Statistics #DataScience #AutoML

Transformers perform remarkable generalizations in the in-context learning setting. E.g. when trained only on step functions, the model generalizes to smooth predictions when given a smooth input. (1/n, a paper thread)

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues Forget my earlier post, this is the cool one! :) Analysis of STATE TRACKING capabilities of "linear RNNs" (GLA, MAMBA, mLSTM). P: arxiv.org/abs/2411.12537

Excited to share our work on this simple yet powerful method for linear RNNs like Mamba or DeltaNet to track states without increasing computational complexity. From CSML IIT Lab and Frank Hutter's group

We are elated to introduce our most recent work on time-series foundation models - Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models. Authors: Omar Swelam, Sathya Kamesh, Julien Siems, David Salinas, Frank Hutter Link: arxiv.org/abs/2410.09385

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

AutoML in the weights of a neural network.