167 citations · 643 across the 64 of their papers we have counts for
11 papers · 1 filter
What Is a Clarification? Estimating Model-Dependent Input Ambiguity
Jingqin Tang, Tim Tomov, Sebastian Schmidt +2
Ambiguous inputs can admit multiple interpretations, each potentially yielding a different answer. Existing work largely treats this ambiguity as a property of the input, yet for a…
Physics-Aligned Electronic Ground-State Learning Improves Generalization
Eike S. Eberhard, Xaver Kainz, Viktor Kotsev +2
Machine-learned interatomic potentials (MLIPs) excel at in-distribution tasks, accelerating drug and material development, yet they struggle to generalize out-of-distribution. We p…
Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization
Yan Scholten, Rachel Lawrence, James Hensman +3
Post-training quantization is a powerful tool for compressing large language models. The most scalable methods quantize every layer in parallel, but quantization errors then compou…
CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Data
Mohamed Amine Ketata, Maximilian Schambach, Stephan Günnemann
Generative models for tabular data are typically trained separately for each dataset, limiting knowledge transfer and requiring the storage of many specialized models. In this pape…
Derivative Informed Learning of Exchange-Correlation Functionals
Eike S. Eberhard, Luca A. Thiede, Abdul Aldossary +5
Machine-learned (ML) exchange-correlation (XC) functionals aim to replace human-designed density functional approximations by learning directly from reference data, but they still…
Task-Aware Calibration: Provably Optimal Decoding in LLMs
Tim Tomov, Dominik Fuchsgruber, Rajeev Verma +1
LLM decoding often relies on the model's predictive distribution to generate an output. Consequently, misalignment with respect to the true generating distribution leads to subopti…
Transferable SCF-Acceleration through Solver-Aligned Initialization Learning
Eike S. Eberhard, Viktor Kotsev, Timm Güthle +1
The cost of Kohn-Sham density functional theory (KS-DFT) calculations scales with the number of solver iterations, which depends on the quality of the initial guess. Machine learni…
EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving
Finn Rasmus Schäfer, Yuan Gao, Dingrui Wang +5
While Vision-Language Models (VLMs) have advanced high-level reasoning in autonomous driving, their ability to ground this reasoning in the underlying physics of ego-motion remains…
A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness
Leo Schwinn, Moritz Ladenburger, Tim Beyer +3
Automated \enquote{LLM-as-a-Judge} frameworks have become the de facto standard for scalable evaluation across natural language processing. For instance, in safety evaluation, thes…
Excited Pfaffians: Generalized Neural Wave Functions Across Structure and State
Nicholas Gao, Till Grutschus, Frank Noé +1
Neural-network wave functions in Variational Monte Carlo (VMC) have achieved great success in accurately representing both ground and excited states. However, achieving sufficient…
A Scalable Multi-Task Model for Virtual Sensors
Leon Götz, Lars Frederik Peiss, Erik Sauer +4
Virtual sensors replace expensive physical sensors in critical applications through machine learning by predicting target signals from available measurements. Existing virtual sens…