Simulation-based inference has really become a commonly used tool for parameter inference across many fields and applications. We (finally...) got together to write a tutorial introduction and guide to (hopefully) help users get started and navigate the different methods and diagnostics!
21.11.2025 15:34 — 👍 38 🔁 11 💬 1 📌 0
The world lost the climate gamble. Now it faces a dangerous new reality
The world bet on collective but voluntary action to keep global warming at a safe level.
"Warming is going to exceed 1.5°C. We are heading into “overshoot” within the next few years. The world is going to become more turbulent and more dangerous. So, what comes after failure?" Some thoughts from Johan Rockstrom & me 10 years after Paris Agreement.
theconversation.com/the-world-lo...
22.11.2025 09:35 — 👍 217 🔁 119 💬 18 📌 20
Second day of #EWRL2025 kicking off with an inspiring talk by Peter Dayan!
“How could it be that we, or an agent, could want something that it does not like, or like something that it would not be willing to exert any effort to acquire?”
18.09.2025 08:08 — 👍 10 🔁 2 💬 0 📌 0
✨ The last day kicked off with an amazing talk by @katjahofmann.bsky.social
"World and Human Action Models for Gameplay Ideation" 🎮🤖
Exciting vision from the Game Intelligence team @msftresearch.bsky.social
19.09.2025 11:31 — 👍 13 🔁 2 💬 0 📌 1
Here at #EWRL: demonstration of autonomous tomato harvesting by polybot.eu
#Robot #Harvesting #Learning
17.09.2025 13:42 — 👍 10 🔁 2 💬 0 📌 0
Fascinating talk by Amy Zhang
on Proto Successor Measures at #EWRL 2025.
euro-workshop-on-reinforcement-learning.github.io/ewrl18/progr...
#reinforcementlearning #robotics #machinelearning
17.09.2025 08:21 — 👍 12 🔁 3 💬 0 📌 0
EWRL18
Just kicked of #EWRL 2025 in Tübingen.
euro-workshop-on-reinforcement-learning.github.io/ewrl18/
Great honor to host this traditional event with Claire Vernade @claireve.bsky.social in Tübingen.
#machinelearning #reinforcementlearning #robotics
17.09.2025 08:20 — 👍 4 🔁 0 💬 0 📌 0
End the Plastic Era!
Right now, just a few powerful polluters are holding the whole world hostage - stopping a Plastics Treaty that could protect our health, wildlife, and planet. Join me today and speak up for a strong g...
Right now, just a few powerful polluters are holding the whole world hostage - stopping a Plastics Treaty that could protect our health, wildlife, and planet. Join me today and speak up for a strong global policy to protect us from plastic pollution! action.wemove.eu/sign/2025-08...
10.09.2025 14:26 — 👍 1 🔁 0 💬 0 📌 0
PheedLoop
PheedLoop: Hybrid, In-Person & Virtual Event Software
📣 Early bird registration ends today!
Register and join us in Tübingen for EWRL 2025: site.pheedloop.com/event/EWRL/h...
03.09.2025 07:44 — 👍 2 🔁 3 💬 0 📌 0
Check out our new preprint where we analyzed the dynamics of over ten thousand neurons across 223 brain areas and found a surprising universal principle that describes the organization of intrinsic timescales across the entire mouse brain, including subcortical structures!
#neuroskyence
03.09.2025 06:52 — 👍 36 🔁 5 💬 0 📌 0
Global sea level is measured by satellite with precision since 1993. A new study compares the data with IPCC projections from the same time. Both the overall rise and its acceleration (the rate of rise has doubled since) are very close to the data.
agupubs.onlinelibrary.wiley.com/doi/10.1029/...
25.08.2025 20:45 — 👍 147 🔁 52 💬 3 📌 2
NSF plans abrupt end to lone U.S. Antarctic research icebreaker
Imminent termination of the RV Nathaniel B. Palmer shocks polar scientists
🌊 ❄️ A running thread on press coverage of the decommissioning of the Research Vessel/Ice Breaker N.B. Palmer (in rough chronological order):
1.- NSF plans abrupt end to lone U.S. Antarctic research icebreaker (Science, July 28th, 2025):
22.08.2025 19:01 — 👍 19 🔁 11 💬 2 📌 2
Es gibt weltweit rund 20.000 Klimaforscher:innen.
Und manche Leute glauben tatsächlich, die seien allesamt dumm oder korrupt, während nur einige wenige in Diensten der fossilen Energiewirtschaft die Wahrheit erzählen. 🙄
20.07.2025 09:16 — 👍 2486 🔁 740 💬 67 📌 21
Sergey Levine was just presenting in the Exploration in AI @ #ICML2025 and promoted that exploration needs to be grounded, and that VLMs are a good source ;-) Check our paper below
👇
19.07.2025 17:47 — 👍 10 🔁 4 💬 0 📌 0
A group of people, some of them at their laptop computers, sitting around a long table, listening.
How can we teach news literacy when TikTok trends shift daily and deepfakes blur reality?
That’s what we explored at the first session of our Multiplier Roundtable for News and Information Literacy in Schools this week in Tübingen. 🚸🧠
16.07.2025 13:23 — 👍 3 🔁 1 💬 1 📌 0
I am going to present the poster during the next poster session. 11am Wed.
Poster W #707
16.07.2025 16:00 — 👍 6 🔁 2 💬 0 📌 0
Philipp Hühn and Markus Flicke at the Award Ceremony of the AI Incubator Demo Day (photo: Tübingen AI Center)
Yesterday, the founding team behind scholar-inbox.com took home the Audience Award 🏆 and the Best Business Model Award 🏆!
Philipp Hühn and @markusflicke.bsky.social impressed everyone with a clear and engaging pitch of their smart recommender tool for academic papers.
11.07.2025 14:48 — 👍 23 🔁 5 💬 1 📌 0
I am in Vancouver at ICML, and tomorrow I will present our newest paper "Partially Observable Reinforcement Learning with Memory Traces". We argue that eligibility traces are more effective than sliding windows as a memory mechanism for RL in POMDPs. 🧵
16.07.2025 01:35 — 👍 59 🔁 12 💬 3 📌 3
In our ICML paper, we study fine-tuning a generalist policy for multiple tasks. We ask, provided a pre-trained policy, how can we maximize multi-task performance with a minimal number of additional demonstrations?
📌 We are presenting a possible solution on Wed, 11am to 1.30pm at B2-B3 W-609!
14.07.2025 19:35 — 👍 10 🔁 4 💬 1 📌 0
✨Introducing SENSEI✨ We bring semantically meaningful exploration to model-based RL using VLMs.
With intrinsic rewards for novel yet useful behaviors, SENSEI showcases strong exploration in MiniHack, Pokémon Red & Robodesk.
Accepted at ICML 2025🎉
Joint work with @cgumbsch.bsky.social
🧵
14.07.2025 08:02 — 👍 22 🔁 5 💬 1 📌 4
YouTube video by Eberhard Karls Universität Tübingen
Mediendozentur 2025 mit Harald Lesch
20. Tübinger #Mediendozentur mit dem Astrophysiker und Bestsellerautor Harald Lesch: Seine Rede „Die informierte Gesellschaft und ihre Feinde“ vom Mittwoch gibt es zum Nachschauen auf dem YouTube-Kanal der Uni: www.youtube.com/watch?v=F91A... #DasWissen #swr #medienwissenschaft #HaraldLesch
27.06.2025 12:49 — 👍 8 🔁 4 💬 0 📌 0
Had great fun in my first ever, live, radio interview, with ORF's Ö1 (Punkt Eins, with Barbara Zeithammer) -- on the occasion of my new professorship at the University of Tübingen @ml4science.bsky.social, talking about AI for Science.
Listen to it here: oe1.orf.at/programm/202...
(54mins, german)
26.06.2025 15:55 — 👍 20 🔁 3 💬 1 📌 0
The 2025 Waymo Challenge results are out! We achieved second place in the End-to-End Driving Challenge with DiffusionLTF and third place in the Scenario Generation Challenge with SHRED. Our approaches prioritized simplicity, and we're preparing to make them publicly available soon.
17.06.2025 21:36 — 👍 15 🔁 5 💬 1 📌 0
Klimapolitik der neuen Regierung: Den Ruf gleich ruiniert
Wie macht man einen guten ersten Eindruck? Das Kabinett von Bundeskanzler Merz hat das bei der Klimapolitik schon mal nicht hinbekommen.
Unser Steuergeld für und zugleich gegen Klimaschutz ausgeben - macht das Sinn???
„Unterm Strich schmeißt die neue Regierung der fossilen Wirtschaft trotz aller Sparschwüre mehr von unseren Steuergeldern in den Rachen als je zuvor – etwa 65 Milliarden im Jahr.“
taz.de/Bernhard-Poe...
15.06.2025 13:48 — 👍 1016 🔁 427 💬 31 📌 25
Bewegungen verstehen – mit Sensoren, KI und Robotik
Dr. Isabell Wochner erklärt, wie ihre Forschung an intelligenten Assistenzsystemen Menschen mit Bewegungseinschränkungen helfen soll – und was ein Pullover damit zu tun hat.
📖 Lesetipp: Dr. Isabell Wochner, Leiterin der Forschungsgruppe "Neuromechanische Modellierung und Sensorfusion für Assistenzrobotik", spricht im Interview mit der Hertie-Stiftung über physikbasierte Assistenzsysteme, die Bewegungen in Echtzeit vorhersagen.
Das ganze Interview: tinyurl.com/5e2zkpcn
16.06.2025 11:21 — 👍 5 🔁 2 💬 0 📌 0
Getting from Tübingen participating in the Huggingface LeRobot hackathon!
#Huggingface #Robotarm #hackathon #PhysicalAI #TuebingenAI
huggingface.co/spaces/LeRob...
14.06.2025 13:41 — 👍 7 🔁 0 💬 0 📌 0
PhD student at the Swiss AI Lab IDSIA USI-SUPSI
https://adityaramesh.in
PhD student at ETH Zurich
jonhue.github.io
Assoc.Prof. in Complex Systems @sydneycompsci.bsky.social @sydney.edu.au. I use information theory to research information processing in complex systems in nature, complex networks, computational neuroscience, etc. Author of JIDT software. Views my own/RTs
Chief Models Officer @ Stealth Startup; Inria & MVA - Ex: Llama @AIatMeta & Gemini and BYOL @GoogleDeepMind
Professor, University of Tübingen @unituebingen.bsky.social.
Head of Department of Computer Science 🎓.
Faculty, Tübingen AI Center 🇩🇪 @tuebingen-ai.bsky.social.
ELLIS Fellow, Founding Board Member 🇪🇺 @ellis.eu.
CV 📷, ML 🧠, Self-Driving 🚗, NLP 🖺
This is the official account of EWRL18 - European Workshop on Reinforcement Learning
Official website: https://euro-workshop-on-reinforcement-learning.github.io/ewrl18/
Postdoc passionate about robotics and AI-driven simulators.
University of Tübingen, AI center
Max Planck Institute for Intelligent Systems, IMPRS-IS Alumni
https://andregeist.github.io
Postdoc @ University of Tübingen | Reinforcement Learning | Optimization | Information Theory
Professor for ML and AI at Lamarr Institute / @tu-dortmund.de. Working on AutoML and Tabular Data. All opinions are my own.
We are a joint partnership of University of Tübingen and Max Planck Institute for Intelligent Systems. We aim at developing robust learning systems and societally responsible AI. https://tuebingen.ai/imprint
https://tuebingen.ai/privacy-policy#c1104
Neuroscience, Machine Learning and Classical Music. Interested in understanding how we move our eyes to behave in the world. Postdoc @bethgelab.bsky.social. Founding Member of grammofy
We accelerate research in the sciences and humanities with machine learning; part of the @ml4science.bsky.social cluster at @unituebingen.bsky.social
Web: mlcolab.org
Member profiles: @sethaxen.com @vstaros.bsky.social
Prof. of Computational Cognitive Science at TU Darmstadt & PI of the Human and Machine Cognition lab at the University of Tübingen | hmc-lab.com
Philosopher of science @ University of Utah.
Formerly research group leader "epistemology and ethics of machine learning" at uni tübingen.
Professor at UT Nuremberg, Germany
I’m 🇫🇷 and I work on RL and lifelong learning. Mostly posting on ML related topics.
Connecting Tübingen's Neuroscience community since 2018. Follow for 🧠 updates, publications, events, jobs, and neuro fun 🧬🧫🥼🔬
📍Tübingen, Germany
Website: https://tuebingenresearchcampus.com/research-in-tuebingen/tnc/
Language models and interpretable machine learning. Postdoc @ Uni Tübingen.
https://sbordt.github.io/
This is the Tübingen research campus of the Max Planck Society in Germany. We do basic research in fields of biology, neuroscience, and AI.
For Institute specific updates follow:
@mpicybernetics.bsky.social
@mpi-bio-fml.bsky.social