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?”

✨ 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

Here at #EWRL: demonstration of autonomous tomato harvesting by polybot.eu #Robot #Harvesting #Learning

Fascinating talk by Amy Zhang on Proto Successor Measures at #EWRL 2025. euro-workshop-on-reinforcement-learning.github.io/ewrl18/progr... #reinforcementlearning #robotics #machinelearning

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

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...

More than 85 scientists say that a recent U.S. Department of Energy report is full of errors and misrepresents climate science.

📣 Early bird registration ends today! Register and join us in Tübingen for EWRL 2025: site.pheedloop.com/event/EWRL/h...

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

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/...

Förderstopp + höhere Netzentgelte? Wirtschaftsministerin Reiche gefährdet die #Photovoltaik auf Dächern. Kommunen, DUH & Verbände fordern: Smart-Meter-Rollout, stabile Regeln & #EnergySharing statt Blockade. ⚠️ #Klimaschutz braucht jede Dachfläche!

🌊 ❄️ 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):

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. 🙄

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 👇

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. 🚸🧠

I am going to present the poster during the next poster session. 11am Wed. Poster W #707

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.

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. 🧵

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!

✨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 🧵

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

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)

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.

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...

Mit unseren Steuergeldern sollte der Staat grundsätzlich nur Aktivitäten mit Subventionen anreizen, die allgemein wünschenswert sind. Mehr Diesel und Bezin verbrennen, mehr Stromverbrauch, mehr Pendeln gehören m.E. nicht dazu. www.spiegel.de/wissenschaft...

📖 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

Getting from Tübingen participating in the Huggingface LeRobot hackathon! #Huggingface #Robotarm #hackathon #PhysicalAI #TuebingenAI huggingface.co/spaces/LeRob...

Hooray! Shaofei's "Relightable Full-body Gaussian Codec Avatars" work neuralbodies.github.io/RFGCA/ is featured in this years SIGGRAPH 2025 Technical Papers Trailer! @acmsiggraph.bsky.social: www.youtube.com/watch?v=HfHC...

⏰ Last hours to submit your paper to EWRL! Don’t miss the chance to present your work to the RL community! If your paper has already been accepted at another conference, we have a fast track submission option this year — with no page limit!⚡ 🗓️ Submission deadline: June 3rd (AoE)

News!⚡ We’re pleased to announce a new Call for Contributed Talks to bring novel and diverse viewpoints to EWRL2025. Early-career researchers are especially encouraged to submit proposals and share their work with the community. Full details: euro-workshop-on-reinforcement-learning.github.io/ewrl18/

Excited to be at the opening of the BITS: Bionic Intelligence Tübingen Stuttgart. www.bionic-intelligence.org Intro by Syn Schmitt. Looking forward to great collaborative research!

Are you based in the U.S. 🇺🇸 or Canada 🇨🇦 and thinking of doing research in Europe? ERC grants offer up to €4.5 million to support groundbreaking, investigator-driven frontier research in all fields. Watch the dedicated info session for researchers in your region👉 youtu.be/92QYink1Lik #ChooseEurope

Since traveling to #cogsci2025 may be particularly difficult this year, we’re hosting a local workshop in Tübingen! 📅 July 24 | Talks & posters + catering supported by @ml4science.bsky.social Open to *everyone*, even without an accepted paper/abstr. 👉 Register by July 1: forms.gle/v6VtEE6UqYw5...

Time to submit your paper! EWRL submissions are open!💫 Check out the Call for Papers here: euro-workshop-on-reinforcement-learning.github.io/ewrl18/

🎤 Meet the speakers! First up: Amy Zhang (amyzhang.github.io), assistant professor at UT Austin and head of the Machine Intelligence through Decision-making and Interaction (MIDI) Lab. Her group works on theory and algorithms for sequential decision-making problems.

🏠 Introducing DepthSplat: a framework that connects Gaussian splatting with single- and multi-view depth estimation. This enables robust depth modeling and high-quality view synthesis with state-of-the-art results on ScanNet, RealEstate10K, and DL3DV. 🔗 haofeixu.github.io/depthsplat/

"The biggest consequence might be losing entire ecosystems before scientists have a chance to understand them."

Working on something cool in RL? Submit it to EWRL! We’ll be opening submissions soon — and this year we’re introducing a fast track for papers already accepted at other conferences! 🚀 Check out the full Call for Papers on the website: euro-workshop-on-reinforcement-learning.github.io/ewrl18/

What if, we knew ... How much "value" is destroyed by damaging the climate (aka our life support system!)? Well we do know now: Let a new era of climate litigation begin! Thanks @ccallahan45.bsky.social @jsmankin.bsky.social Free to read online link: shorturl.at/NIXB3 via @nature.com

🙌 Hot off the presses @natcomms.nature.com! We created a custom #Minecraft environment to study a long-standing puzzle in cognitive science: How do humans flexibly adapt their individual and social learning strategies in dynamic, realistic situations? Check it out 👉 www.nature.com/articles/s41... 🧵👇

🔄 GenFusion bridges 3D reconstruction and generation with a reconstruction-driven video diffusion model. By closing the conditioning gap and fusing restoration frames in a loop, it improves view synthesis from sparse and masked inputs. 🔗 genfusion.sibowu.com #CVPR2025

I am very happy to host EWRL together with @claireve.bsky.social in Tübingen! Looking forward to your submissions and a great community gathering. #RL #Machinelearning #Robotics #EWRL2025

Introducing 3DGSim🧩— an end-to-end 3D physics simulator trained only on multi-view videos. It achieves spatial & temporal consistency w/o ground truth 3D info or heavy inductive biases— enabling scalability & generalization🚀 Kudos to Mikel + @andregeist.bsky.social www.youtube.com/watch?v=3Ar3...

When I got Long Covid, I was 38 and healthy. If you are anything like I was then, it is hard to understand how bad Long Covid is. I think that we all have an instinct to just… look away. But, please, it is important that you look. #LongCovidAwarenessDay

"Free Our Feeds" will unabhängige Bluesky-Infrastruktur in Europa aufbauen, die nicht der US-Gerichtsbarkeit unterliegt. Angesichts des Staatsstreiches in den USA ein sehr wichtiges Ziel. Dafür will man in 8 Wochen drei Millionen Dollar samneln. Bisher hat man aber nur 100.000 Dollar zusammen. 1

Ready to host GSO 2025 in Tübingen. www.guided-self.org/gso-2025.html

Don't miss your chance to register for ELLIS Unit Amsterdam's Winter School on #AI #FoundationModels. The deadline is Jan 26. More info: ivi.fnwi.uva.nl/ellis/events...