Our open-source TPOT AutoML software just reached 10k stars on github! This places TPOT among the top 3,000 highest-ranked repositories, coming in at rank 2,956 github.com/EpistasisLab... #tpot #automl #machinelearning #datascience #artificialintelligence HT @pedroribeiro.bsky.social

🔔 Reminder: 🎓 Interested in a #PhD on #AutoML, #Optimization & #Benchmarking? 🚀 Positions here 👉 automl4science.de/files/2025_J... ⏳ Only six days left to apply!

The final day of #AutoMLConf is dedicated to tutorials & workshops! ☕ CAFE Workshop: peter-i-frazier.github.io/cafe-worksho... 🔍 Tutorials: foundation models, LLM-driven tuning, HPO & more 👉 2025.automl.cc/tutorials/ Sounds interesting? Register now! 2025.automl.cc/registration...

I’m excited to share that I’ll join the Lamarr Institute and @tu-dortmund.bsky.social ‬ as assistant professor in #AutoML and #Optimization this fall 🎉 I’ll continue my research on simplifying the application of machine learning and strengthening rigorous #Benchmarking.

Also, a big shoutout to the TRL organizers @trl-research.bsky.social 🙏

openreview.net/forum?id=vLt... TL;DR: A SoftKNN-based training task makes your ICL model for predictive tabular tasks more intelligible while empirically not decreasing performance.

Greetings from #ACL in Vienna! 👋 Just had a great time presenting our work "In-context learning of Soft Nearest Neighbor Classifiers for Intelligible Tabular Machine Learning" at the Table Representation Learning Workshop. @matthiasfeurer.bsky.social and Mykhailo! 🙌

🚨 Last chance! Early bird tickets for #AutoML2025 in #NYC close Aug 1! Join top experts like Manuela Veloso, Andrew Gordon Wilson & more. 🎟️ 2025.automl.cc/registration... 📝 Submit late-breaking work to the non-archival by Aug 4!

NeurIPS is endorsing EurIPS, an independently-organized meeting which will offer researchers an opportunity to additionally present NeurIPS work in Europe concurrently with NeurIPS. Read more in our blog post and on the EurIPS website: blog.neurips.cc/2025/07/16/n... eurips.cc

EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅 EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu eurips.cc

I'd post exclusively here if @bsky.app would get rid of the silly character limit

🏹 Job alert: Research Scientist at Prior Labs 📍Freiburg or Berlin 🇩🇪 📅 Apply by Dec 31 - preferably earlier 🔗 More info: https://bit.ly/4kqn5rY

Online Now: OpenML: Insights from 10 years and more than a thousand papers #datascience

Last week, @assenmacher.bsky.social (Postdoc at SLDS; leading the NLP focus group) received the Teaching Award for Junior Lecturers 2025 from the Business Administration Student Council WASTI. Great to see that the effort we as a chair put into teaching is rewarded in such a nice way 🙂

@matthiasfeurer.bsky.social @mlindauer.bsky.social @ml4science.bsky.social @balazskegl.bsky.social @klein-aaron.bsky.social @boulesteixlaure.bsky.social @dholzmueller.bsky.social @benjamc.bsky.social

Missed the school? We have uploaded recordings of most talks to our YouTube Channel www.youtube.com/@AutoML_org 🙌

A huge thank you to everyone who joined us at the 5th #AutoML Summer School in Tübingen for four days of talks, hands-on sessions, discussions, great food, and a punting boat trip! Next stop: Dortmund 2026!

We're super happy: Our Cluster of Excellence will continue to receive funding from the German Research Foundation @dfg.de ! Here’s to 7 more years of exciting research at the intersection of #machinelearning and science! Find out more: uni-tuebingen.de/en/research/... #ExcellenceStrategy

Hurry up!! 1 week to go! ⏰

📢 Only 3 Weeks to Go! The AutoML summer school (June 10-13th) is just around the corner, and there is not much time left to register! ---> www.automlschool.org <--- 👇 We added several new speakers to the program

Did you know that #AutoML25 acceptances are out? Congrats to all the authors!👏👏 we are super excited to see these presentations in #NYC! Missed the main track? Submit to the non-archival track by June 16: 2025.automl.cc/call-for-non...

There were layoffs at MS yesterday and 3 #Python core devs from the Faster CPython team were caught in them. If you know of any jobs, please send them their way: Eric Snow: www.linkedin.com/in/ericsnowc... Irit Katriel: www.linkedin.com/in/irit-katr... Mark Shannon: www.linkedin.com/in/mark-shan...

Feature importance measures can clarify or mislead. PFI, LOCO, and SAGE each answer a different question. Understand how to pick the right tool and avoid spurious conclusions: mcml.ai/news/2025-03... @fionaewald.bsky.social @ludwig-bothmann.bsky.social @giuseppe88.bsky.social @gunnark.bsky.social

Thanks to all co-organizers @mlindauer.bsky.social, Frank, Marcel, @matthiasfeurer.bsky.social and Bernd) and also to @ml4science.bsky.social and CyberValley 🙏

The schedule allows for lots of interaction in a poster session, panel discussions, and over lunch. Of course, there will also be a bit of time to enjoy Tübingen 💬🥨

We have an excellent lineup of speakers: @klein-aaron.bsky.social, Anirudh Dagar, @boulesteixlaure.bsky.social, @balazskegl.bsky.social, Bernd Bischl, Jennifer D'Souza, Jonas Geiping, David Salinas, and Maximilian Muschalik. We’re still extending, so stay tuned.

Early Bird registration is still open (until May 1st). The program is shaping up, and our speaker list is growing, so _now_ is the perfect time to secure your spot at a reduced rate! 📅 June 10th-13th, Tübingen, Germany 🔗 www.automlschool.org

We’re getting more and more excited for the 5th AutoML School, happening June 10 - 13 in Tübingen, Germany and we’d love for you to be there.

The 5th NAS Unseen-Data Challenge at #AutoML25 is on! 🥊 How well do your #NAS pipelines perform on completely new, unseen datasets? 📊 Phase 1 is open until June - grab the starter kit and start building! Winners will be announced at #AutoMLConf in #NYC 🗽 More info 👉 www.nascompetition.com

A big 𝘁𝗵𝗮𝗻𝗸 𝘆𝗼𝘂 to everyone who submitted their work for #AutoML25! We received 45 paper submissions in the Main Track and 13 in the ABDC Track. Wow🎉 Now, it's time for our reviewers to get to work 📝 Expect your notifications by May 13! 📆 #AutoMLConf #NYC #AutoML

✏️ The 5th AutoML School w/ a focus on #FoundationModels will be in June in Tübingen. With organisers from @ellisinsttue.bsky.social & ELLIS Unit Freiburg, the school will have intro, state-of-the-art, & application lectures. 📍 Tübingen 🇩🇪 📅 June 10-13 🔗 www.automlschool.org

⏰ REMINDER ⏰ The #AutoMLConf submission deadline is Monday (31/03)! Do you have an #AutoML paper? Submit to a venue with specialized reviewers! Missed out on ICML? This could be your chance for a fresh perspective. Plus, remote presentations are possible if you can't make it to #NYC! Go go go! 🚀

Excited to have Erin LeDell as a #AutoMLConf keynote speaker! Chief Scientist at Distributional & founder of DataScientific, LeDell created H2O AutoML and co-developed the OpenML AutoML Benchmark. A true #AutoML force! Curious to see her in #NYC? 🚨 #AutoML25 submissions close on 31 March! Hurry up!

The #AutoMLConf deadline was extended! We’re looking for groundbreaking contributions in #AutoML, NAS, LLMs, agent-based systems, hyperparameter optimization, benchmarking, algorithm selection, and more. Don’t miss your chance to showcase your work in #NYC! 📅 Deadline: March 31 🌐 CfP: 2025.automl.cc

We're excited to contribute to the 5th AutoML School, co-organized by our own @matthiasfeurer.bsky.social . Bernd Bischl will deliver a tutorial on Bayesian optimization, and we're looking forward to meet many fellow AutoML and ML researchers in Tübingen.

We offer an early bird discount until April 18th and have limited space. Thanks also to @ml4science.bsky.social and CyberValley 🙏

We will also allocate plenty of time to discuss, network and connect with each other and the AutoML community at a poster session, panel discussion, dinner and catered lunch ☕💬🥨 Of course there will be also a bit of time to enjoy the beautiful historic city center and castle of Tübingen!

The schedule will cover all aspects of AutoML, ranging from classic hyperparameter optimization to automated model scaling and pruning, agentic workflows, explainability, and state-of-the-art AutoML systems ✨

It's my pleasure to share the first set of speakers: Aaron Klein, @balazskegl.bsky.social, Bernd Bischl, Jennifer D'Souza, Jonas Geiping, David Salinas, Anirudh Dagar. Many more will follow, stay tuned!

📣 The 5th AutoML School is coming to Tübingen! Whether you are new to #AutoML or an experienced researcher, this is the Summer School for you. Join us for 4 exciting days exploring basic topics, studying cutting edge-research and having fun. 📅 June 10th-13th, Tübingen, Germany 🔗 automlschool.org

Practitioners are often sceptical of academic tabular benchmarks, so I am elated to see that our RealMLP model outperformed boosted trees in two 2nd place Kaggle solutions, for a $10,000 forecasting challenge and a research competition on survival analysis.

Kevin Leyton-Brown joins us as our 3rd keynote speaker! His work on applying machine learning to the automated design and analysis of algorithms for solving hard computational problems makes this speaker particularly relevant to the #AutoML community! 📅 Deadline: March 26 #AutoML25 #AutoMLConf #NYC

Join Lennart Schneider tomorrow for a presentation of our recent #NeurIPS publication "Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization" at the #AutoML seminar at 3PM CET. Link: automl-seminars.github.io Paper: proceedings.neurips.cc/paper_files/...

The first independent evaluation of our RealMLP is here! On a recent 300-dataset benchmark with many baselines, RealMLP takes a shared first place overall. 🔥 Importantly, RealMLP is also relatively CPU-friendly, unlike other SOTA DL models (including TabPFNv2 and TabM). 🧵 1/

𝐀𝐧𝐧𝐨𝐮𝐧𝐜𝐢𝐧𝐠 𝐚𝐮𝐭𝐨𝐦𝐥.𝐬𝐩𝐚𝐜𝐞: 𝐀 𝐂𝐨𝐦𝐦𝐮𝐧𝐢𝐭𝐲 𝐑𝐞𝐬𝐨𝐮𝐫𝐜𝐞 𝐟𝐨𝐫 𝐀𝐮𝐭𝐨𝐌𝐋 We are pleased to announce the launch of automl.space, a web portal designed to serve as a central resource for Automated Machine Learning (AutoML). 🥳 🧵👇

This might be the first time after 10 years that boosted trees are not the best default choice when working with data in tables. Instead a pre-trained neural network is, the new TabPFN, as we just published in Nature 🎉

Happy new Year! We start the new year with some #AutoML content. In September, we had our annual AutoML school, as always, with amazing speakers. Some of the talks are now available online. You can find them via the AV portal of the TIB: av.tib.eu/series/1849

Our MOOC on #AutoML is again online at the AI Campus. We needed to move to a new platform for the last two weeks, but now everything is done. Content-wise nothing changed, but we are already working on a revision of the course -- more updates soon.

Missing AutoML 24? We feel the same! 😢 But don’t worry - you can relive the highlights: 🎥 Watch the talks: www.youtube.com/@automl_conf... 📚 Explore the proceedings: proceedings.mlr.press/v256/ And start planning for AutoML 25! 2025.automl.cc/call-for-pap... #AutoML25 #AutoMLConf #NYC #AutoML

The 3rd Table Representation Learning (TRL) workshop at NeurIPS 2024 is approaching soon ✨ Join us Saturday 14 Dec from 8:30AM for an amazing program and discussions about all things neural models + tabular data (table-representation-learning.github.io ). Not in Vancouver? Join online neurips.cc 😎