3 papers
cs.LG2026
Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport
Luyi Jia, Boyan Zhang, Yilun Liu +1
Diffusion and flow-matching schedules control the signal and noise coefficients that mix data and noise along affine probability paths. Minimizing a kinetic action defined on coeff…
cs.LG2025
Emergent weight morphologies in deep neural networks
Pascal de Jong, Felix Meigel, Steffen Rulands
Whether deep neural networks can exhibit emergent behaviour is not only relevant for understanding how deep learning works, it is also pivotal for estimating potential security ris…
cond-mat.stat-mech2023
Controlling noise with self-organized resetting
Felix J. Meigel, Steffen Rulands
Biological systems often consist of a small number of constituents and are therefore inherently noisy. To function effectively, these systems must employ mechanisms to constrain th…