How can agents learn in long, open-ended tasks where success is rare and rewards are sparse? 👀
🚨 Enter ∆Belief-RL: We show how to use agent’s own belief updates as a dense reward for turn-level credit assignment.
The result? Surprisingly strong generalization.
(1/8) 🧵⬇️
New paper out!🎉
One of our most surprising findings: fine-tuning an LLM on debugging code has unexpected side-effects on contextual privacy. The model learns from printing variables that internal state are ok to share, then generalises this to social situations🤯
A🧵below👇
The 6th Workshop on Human-Centered Explainable AI is happening at CHI 2026 in Barcelona. It's been a great research community. You should submit a paper. Deadline is February 19th.
This year's theme is agentic AI, but all human-centered XAI topics are welcome.
Scholar Inbox in conference mode is soooo useful. Get your poster session recommendations with the poster number and access the paper....
Thanks @andreasgeiger.bsky.social and team!
Finally got the job ad—looking for 2 PhD students to start spring next year:
www.gao-unit.com/join-us/
If comp neuro, ML, and AI4Neuro is your thing, or you just nerd out over brain recordings, apply!
I'm at neurips. DM me here / on the conference app or email if you want to meet 🏖️🌮
Excited to be at #Neurips2025 this week to present our paper "Monoculture or Multiplicity: Which is it?", joint work with Moritz Hardt.
📄 Paper #1000: openreview.net/pdf?id=DO5Lt...
📍 Wed, Dec 3, 2025 • 4:30 PM – 7:30 PM
Feel free to come by and reach out!
A short 🧵.
At #NeurIPS in San Diego this week? Interested in XAI, causality, or performative prediction? Come visit our poster!
💬 Performative Validity of Recourse Explanations
📆 Wednesday, 4.30 pm, Poster Session 2
w/ Hidde Fokkema, Timo Freiesleben, Celestine Mendler-Dünner, Ulrike von Luxburg
🚨 New paper at #NeurIPS2025!
A systematic fixation-level comparison of a performance-optimized DNN scanpath model and a mechanistic cognitive model reveals behaviourally relevant mechanisms that can be added to the mechanistic model to substantially improve performance.
🧵👇
The Tübingen AI Research Building, where the Cluster of Excellence "Machine Learning: New Perspectives for Science" is based: A four-story, beige-colored building with numerous window fronts. In front of it stand four trees with autumn leaves.
We are looking for several postdoctoral researchers to join our Norms & Practices Lab! This is an exciting opportunity for scholars of #philosophy, #law, #culturalanthropology, and (qualitative) #socialscience: uni-tuebingen.de/en/128980#c2... 1/2
Tübingen Conference for AI and Law starting on wednesday!
Keynotes by Rediet Abebe, Solon Borocas, Sylvie Delacroix, Lilian Edwards, Christoph Engel, Michal Gal, Philipp Hacker, Christoph Kern, Christoph Sorge.
ailawinstitute.de/conference-f...
Super happy to be recognised as a top reviewer for this year's NeurIPS :) Thanks @neuripsconf.bsky.social for the free ticket and see you in San Diego in Dec!
Hamburg just said YES in the climate referendum! ♥️
Thanks to everyone who fought for it.
This vote matters for Hamburg – and sends a strong signal far beyond.
The climate issue is alive: we can set the agenda and win!
Another lesson: climate action must go hand in hand with social justice.
🚨 Workshop on the Theory of Explainable Machine Learning
Call for ≤2 page extended abstract submissions by October 15 now open!
📍 Ellis UnConference in Copenhagen
📅 Dec. 2
🔗 More info: sites.google.com/view/theory-...
@gunnark.bsky.social @ulrikeluxburg.bsky.social @emmanuelesposito.bsky.social
📣 New Preprint!
Have you ever wondered what the political content in LLM's training data is? What are the political opinions expressed? What is the proportion of left- vs right-leaning documents in the pre- and post-training data? Do they correlate with the political biases reflected in models?
We have a new paper out today, and I’m so proud of it and the work that went into creating it! Link here: arxiv.org/pdf/2509.184....
The 2024 US presidential election was the first major election in the US since the popularization of LLMs. (1/6)
I've been waiting some years to make this joke and now it’s real:
I conned somebody into giving me a faculty job!
I’m starting as a W1 Tenure-Track Professor at Goethe University Frankfurt in a week (lol), in the Faculty of CS and Math
and I'm recruiting PhD students 🤗
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
NeurIPS has decided to do what ICLR did: As a SAC I received the message 👇 This is wrong! If the review process cannot handle so many papers, the conference needs yo split instead of arbitrarily rejecting 400 papers.
🎉 Delighted to announce that our 🫗Leaky Thoughts paper about contextual privacy with reasoning models is accepted to #EMNLP main!
Huge congrats to the amazing team Tommaso Green, Haritz Puerto @coallaoh.bsky.social @oodgnas.bsky.social
Are you afraid of LLMs teaching people how to build bioweapons? Have you tried just... not teaching LLMs about bioweapons?
@eleutherai.bsky.social and the UK AISI joined forces to see what would happen, pretraining three 6.9B models for 500B tokens and producing 15 total models to study
eXCV Workshop at ICCV 2025, Submission deadline August 15.
Are you an XAI researcher attending #ICCV2025? Submit your recently published work — at CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI etc. — to the eXCV Workshop for the opportunity to further showcase your work! Published papers can be submitted as is, no rewriting necessary.
@iccv.bsky.social
Shoulder portrait of Nicole Ludwig in front of a stone wall (photo: Cluster of Excellence: Machine Learning for Science / Elia Schmid)
We’re excited to welcome @nicoleludwig.bsky.social as a Junior Professor for Climate, Energy & Machine Learning Systems!
Learn more: →https://tuebingen.ai/news/junior-professor-nicole-ludwig-joins-tuebingen-ai-center
@unituebingen.bsky.social @mwk-bw.bsky.social @ml4science.bsky.social
Meet @elinguyen.bsky.social, our Winter 2025 Research Intern who traveled all the way from Germany to explore new research perspectives!
Inspired to start your own journey?
Applications for Vector's Winter 2026 Research Internships are open! Apply now:
vectorinstitute.ai/programs/res...
Das Bild zeigt einen Flyer von "I'm a Scientist". Auf dem Bild steht "Start der Themenrunde KI und Bildung. Live-Chats vom 19.-23. Mai. Darunter ist ein alter Computer mit Pixelart auf dem Bildschirm abgebildet. Ein junges Mädchen, das aus einem Ölgemälde ausgeschnitten wurde, sitzt am Computer und schreibt.
👩🏫 Heute startet die Themenrunde "KI und Bildung" bei #ImaScientist @w-i-d.de - wir wünschen allen beteiligten Forschenden und Schulklassen interessante Gespräche, einen schönen Austausch und sind schon gespannt, welche:r der Forschenden das Rennen als Lieblingswissenschaftler:in macht! 👩🔬👩🎓
"Forscher*innen für neue Themenrunde gesucht". Logo I'm a Scientist, "KI und Bildung", "Noch bis zum 27. April bewerben. Logo Wissenschaft im Dialog, RHET AI, Volkswagen Stiftung, Forschungsbörse
Für die kommende Themenrunde von I’m a Scientist suchen wir Wissenschaftler*innen, die zum Einfluss von KI auf den Bildungsbereich forschen. Die Live-Chats mit Schüler*innen finden vom 19. bis 23. Mai statt. Bis zum 27. April bewerben: imascientist.de/bewerbungsfo...
#Wisskomm
Fantastic initiative by @serge.belongie.com and Søren Hauberg 🇪🇺🇩🇰
Please take a moment to answer through the poll below and share in your networks! 👇
Screenshot of the first page of the paper available at https://arxiv.org/abs/2502.08554
Appropriate reliance is key to safe and successful user interactions with LLMs. But what shapes user reliance on LLMs, and how can we foster appropriate reliance?
In our #CHI2025 paper, we explore these questions through two user studies.
1/7
I've recently put together a "Fairness FAQ": tinyurl.com/fairness-faq. If you work in non-fairness ML and you've heard about fairness, perhaps you've wondered things like what the best definitions of fairness are, and whether we can train algorithms that optimize for it.
Happy #InternationalWomensDay! As we celebrate the achievements of women everywhere today, a special shoutout to all women in science from us - from the trailblazers & changemakers to today’s innovators shaping the future. Thank you for your curiosity, courage & for redefining what’s possible!
🤗🔬💜
I will be giving a talk at the MPI-IS @maxplanckcampus.bsky.social in Tübingen next week (March 12 @ 11am). The talk will cover my group's overall approach to trust in ML, with a focus on our work on unlearning and how to obtain verifiable guarantees of trust.
Details: is.mpg.de/events/speci...
