17 citations · 19 across the 11 of their papers we have counts for
12 papers
Kolibri: A Sovereign European Model on the Pareto Frontier
Aleph Alpha, :, Moritz Althaus +65
This report introduces Kolibri, an English-German mixture-of-experts transformer with 78.1B total parameters and 3.46B active parameters per token, released as open weights under t…
Exact Quantile Balancing and Load-Error Injection for Mixture-of-Experts
Pit Neitemeier, Jiaze Li, Alessio Serra +2
Mixture-of-Experts (MoE) training requires global load balance to prevent expert under-utilization and local balance for efficient expert-parallel execution. Existing distributed Q…
Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack
Sohir Maskey, Philipp Scholl, Jonas Knupp +2
Language-model checkpoints are commonly selected by pretraining loss or benchmark scores, assuming that the highest-scoring checkpoint will remain the best starting point for subse…
When is a System Discoverable from Data? Discovery Requires Chaos
Zakhar Shumaylov, Peter Zaika, Philipp Scholl +3
The deep learning revolution has enabled major AI advances in physical sciences, particularly in discovering dynamical systems from observational data. Yet the reliability of learn…
Improved probabilistic regression using diffusion models
Carlo Kneissl, Christopher Bülte, Philipp Scholl +1
Probabilistic regression models the entire predictive distribution of a response variable, offering richer insights than classical point estimates and directly allowing for uncerta…
Interpretable Robotic Friction Learning via Symbolic Regression
Philipp Scholl, Alexander Dietrich, Sebastian Wolf +4
Accurately modeling the friction torque in robotic joints has long been challenging due to the request for a robust mathematical description. Traditional model-based approaches are…
Graph Neural Networks for Enhancing Ensemble Forecasts of Extreme Rainfall
Christopher Bülte, Sohir Maskey, Philipp Scholl +2
Climate change is increasing the occurrence of extreme precipitation events, threatening infrastructure, agriculture, and public safety. Ensemble prediction systems provide probabi…
Probabilistic neural operators for functional uncertainty quantification
Christopher Bülte, Philipp Scholl, Gitta Kutyniok
Neural operators aim to approximate the solution operator of a system of differential equations purely from data. They have shown immense success in modeling complex dynamical syst…
Robust identifiability for symbolic recovery of differential equations
Hillary Hauger, Philipp Scholl, Gitta Kutyniok
Recent advancements in machine learning have transformed the discovery of physical laws, moving from manual derivation to data-driven methods that simultaneously learn both the str…
Compositional Construction of Barrier Functions for Switched Impulsive Systems
Katharina Bieker, Hugo Tadashi Kussaba, Philipp Scholl +4
Many systems occurring in real-world applications, such as controlling the motions of robots or modeling the spread of diseases, are switched impulsive systems. To ensure that the…
Learning-based adaption of robotic friction models
Philipp Scholl, Maged Iskandar, Sebastian Wolf +5
In the Fourth Industrial Revolution, wherein artificial intelligence and the automation of machines occupy a central role, the deployment of robots is indispensable. However, the m…
ParFam -- (Neural Guided) Symbolic Regression Based on Continuous Global Optimization
Philipp Scholl, Katharina Bieker, Hillary Hauger +1
The problem of symbolic regression (SR) arises in many different applications, such as identifying physical laws or deriving mathematical equations describing the behavior of finan…