2 papers
cs.LG2026
Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking
Kyungwon Jeong, Won-Gi Paeng, Honggyo Suh
Weight matrices in deep networks exhibit geometric continuity -- principal singular vectors of adjacent layers point in similar directions. While this property has been widely obse…
hep-ph2025
Folded Context Condensation in Path Integral Formalism for Infinite Context Transformers
Won-Gi Paeng, Daesuk Kwon, Kyungwon Jeong +1
In this work, we present a generalized formulation of the Transformer algorithm by reinterpreting its core mechanisms within the framework of Path Integral formalism. In this persp…