2 papers
cond-mat.dis-nn2026
Learning Dynamics of Chain-of-Thought State Tracking in a Solvable Transformer Model
Niklas Forner, Marcel Kühn, Matthias Thamm +1
Chain-of-thought generation can turn a multi-step computation into a sequence of locally checkable state updates, but the training dynamics by which transformers acquire such updat…
cond-mat.dis-nn2025
BBP Phase Transition for an Extensive Number of Outliers
Niklas Forner, Alexander Maloney, Bernd Rosenow
Random-matrix theory helps disentangle signal from noise in large data sets. We analyze rectangular matrices in which the noise generates a Marchenko…