3 papers
cs.LG2026
On Foundation Models for Temporal Point Processes to Accelerate Scientific Discovery
David Berghaus, Patrick Seifner, Kostadin Cvejoski +1
Many scientific fields, from medicine to seismology, rely on analyzing sequences of events over time to understand complex systems. Traditionally, machine learning models must be b…
cs.LG2026
Towards Fast Coarse-graining and Equation Discovery with Foundation Inference Models
Manuel Hinz, Maximilian Mauel, Patrick Seifner +3
High-dimensional recordings of dynamical processes are often characterized by a much smaller set of effective variables, evolving on low-dimensional manifolds. Identifying these la…
cs.LG2025
Towards Foundation Inference Models that Learn ODEs In-Context
Maximilian Mauel, Manuel Hinz, Patrick Seifner +2
Ordinary differential equations (ODEs) describe dynamical systems evolving deterministically in continuous time. Accurate data-driven modeling of systems as ODEs, a central problem…