Robert Bamler
34 posts
@robamler
Professor of Data Science and Machine Learning at @uni_tue, member of @ml4science and Tübingen AI Center.
✨ New paper: Flipping Against All Odds We found that large language models (LLMs) can describe probabilities—but fail to sample from them faithfully. Yes, even flipping a fair coin is hard. 🪙 🧵 Here’s what we learned—and how we fixed it. 🔗arxiv.org/abs/2506.09998 1/
Differentiable annealed importance sampling (DAIS) minimizes the Jensen-Shannon divergence between its initial and target distribution! Check out our work (arxiv.org/abs/2405.14840) with @robamler and meet us at the poster at ICML in Hall C 4-9 #2610 in the morning session today!
🚨The training and test set of the Street View House Numbers (SVHN) dataset are NOT from the same distribution!🚨 Join us at the #NeurIPS2023 workshop on DistShift this Friday (10:30 am, room R06-R09) to find out more! arxiv.org/abs/2312.02168 w/ @johanneszenn @robamler
My student @johanneszenn found a useful fact about differential sequential Monte Carlo samplers: you can ignore any gradients due to resampling because they vanish in expectation. Check out his accepted ICLR DEI paper and meet us at the poster on Friday. arxiv.org/abs/2304.14390
🎉Exciting news! Our "Neural Compression" workshop proposal has been accepted at #ICML 2023! Join us to explore the latest research developments, including perceptual losses and more compute-efficient models! @BerivanISIK, @YiboYang, @_dsevero, @karen_ullrich, @robamler
2⃣ Wie viel Science steckt in der Fiction? Filmvorführung "Ex Machina" und Diskussion; mit Lukas Kohmann und Anne Burkhardt von RHET AI – und @robamler von @ml4science Eintritt frei! Zur Anmeldung (und dem ganzen Programm): #1565282panel-11-pc" target="_blank" rel="nofollow noopener">uni-tuebingen.de/#1565282panel-…
