iiinova — where your digital self keeps evolving

Reposted by Bennet Wittelsbach

Emtiyaz Khan @emtiyaz.mastodon.social.ap.brid.gy · 15/10/2026

I recently moved to TU Darmstadt (Germany) and am currently hiring PhD student through ELISS. ellis.eu/news/ellis-phd-program-cal… If you interested, please apply and choose me as a potential advisor. Topics include Continual/Distributed/Federated/Active/Transparent […]

mastodon.social

Original post on mastodon.social

0116

Reposted by Bennet Wittelsbach

Computer Science, TU Darmstadt @cs-tudarmstadt.bsky.social · 20/08/2026

🥳 KI-Pionierin Prof. Leslie Pack Kaelbling vom MIT eröffnet unsere neue Distinguished Lecture Series mit "Rational Robots" – eine einmalige Chance, sie an der TU Darmstadt live zu erleben. 📅 2.10., 14 Uhr, Maschinenhaus 🔗 Infos und Anmeldelink unter: www.informatik.tu-darmstadt.de/fb20/ueber_u...

264

Reposted by Bennet Wittelsbach

Andreas Grivas @andreasgrv.bsky.social · 10/07/2026

Missed our poster on byte-level LLMs at ICLR on Tuesday? Come chat to us at the CoLoRAI workshop tomorrow afternoon at 15:15! grigoris.ece.wisc.edu/workshops/co... @emilevankrieken.com @nolovedeeplearning.bsky.social

Andreas Grivas, Emile van Krieken and Antonio Vergari presenting the poster "Fast and Expressive Multi-Byte Prediction with Probabilistic Circuits"

1124

Bennet Wittelsbach @bewit.bsky.social · 10/07/2026

Happening tomorrow, lots of cool talks, check them out! And feel free to stop by my poster "Membership Circuits" at 15:30 to see if we can obtain formal guarantees with learned models 🤗

140

Reposted by Bennet Wittelsbach

Mark Rothermel @mrothermel.bsky.social · 07/05/2026

We are proud to announce the release of our (ACL 2026 Oral) benchmark, VeriTaS, for measuring the fact-checking capabilities of LLM agents! In a world of growing fake news, we believe that the ability to verify claims is critical. VeriTaS is multimodal, multilingual, and made of real-world claims.

221

Reposted by Bennet Wittelsbach

Randall Munroe @xkcd.com · 08/07/2026

Offside xkcd.com/3268/

Comic. [chessboard with red dotted line and flag at second line. Highlighted rook is positioned next to King behind the red line.] [caption] I thought I had checkmate, but I didn’t realize my rook was offside.

464598816

Reposted by Bennet Wittelsbach

Symposium on Probabilistic Machine Learning @probml.bsky.social · 05/07/2026

Excited that our ProbML symposium has now started (and is online on zoom: link is on probml.cc/schedule )! We have a full day of talks and posters on probabilistic machine learning.

0118

Bennet Wittelsbach @bewit.bsky.social · 04/07/2026

Just arrived in Seoul to join ProbML and ICML. Looking forward to many interesting talks and discussions 😊 (I will also present a poster at the Hypothesis Testing in Machine Learning workshop on saturday, details coming!)

040

Reposted by Bennet Wittelsbach

Moritz Schauer @mschauer.bsky.social · 01/07/2026

The redeeming feature is that this price is paid only once.

Right, you don't need error bars on error bars.
Probabilistic uncertainty about uncertainty collapses. This is the “monadic join” in probability.
Instead of a coin with random bias p ∼ π, you can flip a coin with the deterministic bias μ.
Just take μ = E[p].

161

Reposted by Bennet Wittelsbach

Tomer Ullman @tomerullman.bsky.social · 15/06/2026

"the new toaster says 'I Love You' when you put the toast in, and 'I'm Sorry' when it burns it. This causes some people to get angry b/c they don't think the toaster means it, and others to develop unhealthy attachments b/c they think it does. the solution is to make the toaster TRULY sorry"

2349

Bennet Wittelsbach @bewit.bsky.social · 20/03/2026

Wrapping up my first week as a PhD candidate with @hessianai.bsky.social. I got to know very welcoming and smart people working on Multimodal AI in Marcus Rohrbach's lab. What role will Probabilistic Circuits play in a multimodal world? @kerstingaiml.bsky.social Really excited for what's ahead!

030

Reposted by Bennet Wittelsbach

Guy Van den Broeck @guyvdb.bsky.social · 04/03/2026

We put probabilistic circuits into diffusion language models and got a big boost in reasoning performance!

0172

Reposted by Bennet Wittelsbach

Antonia Wüst @toniwuest.bsky.social · 30/11/2025

🚨 New paper alert! We introduce Vision-Language Programs (VLP), a neuro-symbolic framework that combines the perceptual power of VLMs with program synthesis for robust visual reasoning.

1157

Reposted by Bennet Wittelsbach

wolfstammer.bsky.social @wolfstammer.bsky.social · 07/07/2025

Can concept-based models handle complex, object-rich images? We think so! Meet Object-Centric Concept Bottlenecks (OCB) — adding object-awareness to interpretable AI. Led by David Steinmann w/ @toniwuest.bsky.social & @kerstingaiml.bsky.social . 📄 arxiv.org/abs/2505.244... #AI #XAI #NeSy #CBM #ML

0104

Reposted by Bennet Wittelsbach

Thomas Dietterich @tdietterich.bsky.social · 15/06/2025

I think we should be building systems that complement people; systems that do well the things that people do poorly; systems that make individuals and organizations more effective and more humane. 3/

14212

Reposted by Bennet Wittelsbach

Kristian Kersting @kerstingaiml.bsky.social · 24/05/2025

🚀 TU Darmstadt leads the new Cluster of Excellence "Reasonable AI" – advancing trustworthy, efficient & adaptive AI grounded in common sense. A big thank you to the entire team, the university, and the state of Hesse for their tremendous work & support!

buff.ly

Reasonable and safe: The future of artificial intelligence

The researchers in the new Cluster of Excellence “Reasonable Artificial Intelligence” (RAI) , which is headed by TU Darmstadt, are carrying out research into a new generation of artificial…

3274

Reposted by Bennet Wittelsbach

Martin Mundt @martinmundt.bsky.social · 08/05/2025

Horizontal, vertical, hybrid data partitioning: heterogeneity is tough to handle in federated learning! 🔥In “Scaling Probabilistic Circuits via Data Partitioning" - accepted at #UAI25 - we unify the different settings through aggregation of learned client distributions: arxiv.org/abs/2503.08141

074

Reposted by Bennet Wittelsbach

Antonia Wüst @toniwuest.bsky.social · 02/05/2025

Excited to share that our paper got accepted at #ICML2025!! 🎉 We challenge Vision-Language Models like OpenAI’s o1 with Bongard problems, classic visual reasoning challenges and uncover surprising shortcomings. Check out the paper: arxiv.org/abs/2410.19546 & read more below 👇

12410

Reposted by Bennet Wittelsbach

Moritz Willig @moritzwillig.bsky.social · 17/04/2025

I'm excited to present our spotlight on meta-causal models at #ICLR2025 next week. We model evolving causal graphs in dynamic systems. Applications to inference and attribution of agent actions. Paper: openreview.net/forum?id=J9V... Visit our poster #441 during the Sat 3pm session.

1155

Reposted by Bennet Wittelsbach

Martin Trapp @trappmartin.eurosky.social · 22/03/2025

Feel in meme mode today. 😅

0142

Reposted by Bennet Wittelsbach

Lorenzo Loconte @loreloc.bsky.social · 12/02/2025

Happy to see our work at TMLR! We systematically show the relationships between two apparently different fields: tensor factorizations and circuits, and how bridging the two enables us to exchange results, research opportunitie in ML, and practical implementation solutions.

0204

Reposted by Bennet Wittelsbach

Kristian Kersting @kerstingaiml.bsky.social · 24/01/2025

Thrilled to share our #ICLR2025 work on Meta-Causal States! 🌟 Causal graphs evolve with dynamic systems & agent actions. We show how to cluster causal models by qualitative behavior, revealing hidden dynamics & emergent relationships 🚀 #Causality #ML arxiv.org/abs/2410.13054

0126

Reposted by Bennet Wittelsbach

Sriraam Natarajan @nsriraam.bsky.social · 21/12/2024

When building human allied AI systems, it is imperative to think of who is in control. In our blue sky paper at #AAAI, we argue that a deeper understanding of whether human is in the loop or if AI is in the loop is essential! arxiv.org/pdf/2412.14232

1167

Reposted by Bennet Wittelsbach