Author

M. Wiemann

h-index 4 View on Semantic Scholar

We have 2 of 8 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance

It is shown that the effect of interleaved noise injection stems from penalizing the failure modes encouraged by the inductive bias of the models: impulse noise works against the locality bias of convolutional (ResNet) architectures, and Gaussian noise reduces the tendency of attention-based models to pick up large-sca...

M. Wiemann, Peter Melchior, A. Saydjari · arXiv.org · 0 citations

#machine learning May 2026

DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking

DiscoverPhysics, an interactive benchmark that asks a LLM agent to discover the laws of motion of a simulated world whose physics deliberately deviates from the authors' own, is introduced.

M. Wiemann, Lindsay M. Smith, Peter Melchior et al. · arXiv.org · 12 citations · ⚡2