Conveners
🌟 Highlight talks
- There are no conveners in this block
🌟 Highlight talks
- Jan M. Pawlowski (Heidelberg University)
-
Henning Rose (Uni Hamburg)28/08/2026, 09:00
Autoregressive transformers are increasingly applied outside the language domain that motivated them, but the tokenization step transfers poorly. Scientific data are already numerical, often partly discrete, and typically live in high-dimensional spaces where each token carries several features. The standard workaround, compressing feature vectors into a single token via a learned codebook,...
Go to contribution page -
194. Highlight Talk: Low-cost Adaptation of a Geometry Foundation Model for Bayesian Shape InferenceThomas Gessey-Jones (PhysicsX)28/08/2026, 09:30
Inferring a three-dimensional shape from sparse, indirect measurements is a severely ill-posed inverse problem, which arises throughout the physical and biological sciences. Doing so successfully with principled Bayesian uncertainties requires a tractable parametrisation of geometry, and a strong prior encoding domain knowledge of plausible shapes.
In this talk we show how a pretrained...
Go to contribution page -
Yong Sheng Koay (Uppsala University)28/08/2026, 10:00
Foundation models embed not only their training examples but the space those examples were drawn from. A transformer trained to write Lagrangians symbolically (such as BART-L) thus embeds the space of theories itself. In this work, we investigate the navigation of this learned theory space using activation steering, adapted from interpretability work on LLMs. Using only small contrastive...
Go to contribution page -
Jesus Pena-Rodriguez (JLU Giessen)28/08/2026, 11:00
SiPMs (Silicon Photomultipliers) have recently been studied as candidates for building photon cameras in RICH (Ring Imaging Cherenkov) detectors. SiPM-based cameras improve detection efficiency (up to
Go to contribution page
), spatial resolution (mm), timing (
\, ps), scalability, and magnetic field immunity. Nevertheless, for single-photon detection, SiPM thermal noise (
\,kHz/mm
) and photon-background... -
Gianluca Inguglia (MBI Vienna)28/08/2026, 11:30
We present an anomaly detection algorithm based on a deep convolutional autoencoder. The algorithm, initially developed with a focus on the Einstein Telescope, was adjusted to the higher noise levels of the LIGO detectors, implementing coherence, trained and validated using O3 data, and tested on publicly available O4 data. We achieve an excellent recovery rate for short, loud signals and...
Go to contribution page