51 citations · 52 across the 4 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Architecture-agnostic Lipschitz-constant Bayesian header and its application to resolve semantically proximal classification errors with vision transformers
Frederik Schäfer, Luis Mandl, Lars Kälber +1
Label noise remains a critical bottleneck for the generalization of supervised deep learning models, particularly when errors are structured rather than random. Standard robust tra…
physics.comp-ph2026
SPINONet: Scalable Spiking Physics-informed Neural Operator for Computational Mechanics Applications
Shailesh Garg, Luis Mandl, Somdatta Goswami +1
Energy efficiency remains a critical challenge in deploying physics-informed operator learning models for computational mechanics and scientific computing, particularly in power-co…