A new recording of our FridayTalks@Tübingen series is online! SoftJAX & SoftTorch: Soft Differentiable Programming for Scientific Machine Learning by @andregeist.bsky.social Watch here: youtu.be/7Q8tuxDGP-Y

The Breach: When AI Starts to Cheat 🚨 New research by PIs Jonas Geiping and Maksym Andriushchenko says we have a major blind spot. Most safety systems plan to rely on a smaller monitor model to watch over an untrusted AI agent. 👉 institute-tue.ellis.eu/en/news/the-...

A new recording of our FridayTalks@Tübingen series is online! Training Dynamics Impact Post-Training Quantization Robustness by Albert Catalán-Tatjer Watch here: youtu.be/_G_TA3THjiw

A new recording of our FridayTalks@Tübingen series is online! Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding by Alexander Conzelmann Watch here: youtu.be/CsXDtg4w9hM

A new recording of our FridayTalks@Tübingen series is online! Adaptive Symmetrization of the KL Divergence by @omribendov.bsky.social Watch here: youtu.be/VPu1Rd4TmkU

A new recording of our FridayTalks@Tübingen series is online! Flexible Gravitational-Wave Parameter Estimation with Transformers by @annalenakofler.bsky.social Watch here: youtu.be/WPpZBYvHr0A

A new recording of our FridayTalks@Tübingen series is online! The Value of Ambiguous Commitment in Multi-Follower Games by Rabanus Derr Watch here: youtu.be/scQxHRVC0Cw

A new recording of our FridayTalks@Tübingen series is online! Physics of Learning by Siyuan Guo Watch here: youtu.be/T6CMXNndQn0

A new recording of our FridayTalks@Tübingen series is online! PENEX: AdaBoost-Inspired Neural Network Regularization by @kkladny.bsky.social Watch here: youtu.be/C2HmBlrPi6c

A new recording of our FridayTalks@Tübingen series is online! Strategic Hypothesis Testing by @yatongchen.bsky.social Watch here: youtu.be/VcKpRuUi4cQ

🚀 The new call for Principal Investigators as Hector Endowed Fellows at the ELLIS Institute Tübingen is now open! These positions offer the exciting possibility of co-appointments with the @mpi-is.bsky.social and the @tuebingen-ai.bsky.social . 📌 Apply here: institute-tue.ellis.eu/en/jobs/PI-c...

A new recording of our FridayTalks@Tübingen series is online! The Curse of Depth in Large Language Models by @shiweiliu.bsky.social Watch here: youtu.be/knVOH3oM_-I

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 🤗

A new recording of our FridayTalks@Tübingen series is online! AI Safety and Alignment by @maksym-andr.bsky.social Watch here: youtu.be/7WRW8MDQ8bk

A new recording of our FridayTalks@Tübingen series is online! Why LLM Benchmarks are Broken and How to Fix It? by Guanhua Zhang Watch here: youtu.be/X820NwnHu-c

Want to get started with theoretical analysis of probabilistic decision-making algos (bandits, BO, planning, etc.), but don't know where to start? Existing literature too dense to parse? arxiv.org/abs/2508.21620 I've written a self-contained introductory monograph on this!

A new recording of our FridayTalks@Tübingen series is online! How much can we forget about Data Contamination? by @sbordt.bsky.social Watch here: youtu.be/T9Y5-rngOLg

A new recording of our FridayTalks@Tübingen series is online! Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics by @chs20.bsky.social & Naman Deep Singh Watch here: www.youtube.com/watch?v=sK9Y...

A new recording of our FridayTalks@Tübingen series is online! Large Language Models Are Zero-Shot Problem Solvers—Just Like Modern Computers by Tim Z. Xiao Watch here: www.youtube.com/watch?v=ySHu...

A new recording of our FridayTalks@Tübingen series is online! Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Models by @vetterj.bsky.social & Manuel Gloeckler from @mackelab.bsky.social Watch here: youtube.com/watch?v=Wx2p...

📣 [Openings] I'm now an Assistant Prof @westernu.ca CS dept. Funded PhD & MSc positions available! Topics: large probabilistic models, decision-making under uncertainty, and apps in AI4Science. More on agustinus.kristia.de/openings/

@unituebingen.bsky.social Tübingen has won 6 out of 9! Not too bad, is it? 👍 Congratulations to all winning teams!

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

Die Universität Tübingen erhält sechs #Exzellenzcluster, die im Rahmen der #Exzellenzstrategie vom 01.01.2026 an sieben Jahre lang gefördert werden! Darunter drei Cluster, die bereits etabliert sind und eine erneute Förderung erhalten. uni-tuebingen.de/universitaet... #ExStra #Forschung #UniTübingen

I'm extremely disappointed with the organization of the upcoming German election. Voting is a fundamental right, yet my ballot letter arrived too late in Toronto—now the fastest! delivery won't get it there by Monday, after the election. Unacceptable.

I am happy to share that we (finally!) took the time to publish parts of my Master's thesis as a paper (pubs.rsc.org/en/content/a...). Huge thanks to Dominik Gond, Fabian Jirasek and Robert Bamler. Check it out if you are interested in applications of machine learning to chemical engineering!

Can we build neural networks whose structure and computational abilities match a real brain? We are not quite there yet, but recent work by @lappalainenjk.bsky.social et al. shows a strategy for getting closer to this goal. Read more on our blog: www.machinelearningforscience.de/en/improving...

How to find all fixed points in piece-wise linear recurrent neural networks (RNNs)? A short thread 🧵 
In RNNs with N units with ReLU(x-b) activations the phase space is partioned in 2^N regions by hyperplanes at x=b 1/7

@jkapoor.bsky.social and @auschulz.bsky.social introduce LDNS, a diffusion-based latent variable model to generate diverse neural spiking data flexibly conditioned on external variables Poster #4010 (East; Wed 11 Dec 11PT) ➡️ openreview.net/forum?id=ZX6... 3/4

@vetterj.bsky.social and I are excited to present our work at #NeurIPS2024! We present Sourcerer: a maximum-entropy, sample-based solution to source distribution estimation. Paper: openreview.net/forum?id=0cg... Code: github.com/mackelab/sou... (1/8)

I am super hyped and happy with our recent paper on a ✨VampPrior 2.0✨: Hierarchical VAE with a diffusion-based VampPrior! 🦇 We got SOTA VAE results on CIFAR-10! Kudos to Anna Kuzina because this TMLR paper is the last chapter in her PhD thesis 🤩 📃 tinyurl.com/22rvzc4f 💻 github.com/AKuzina/dvp_...