Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Understanding Learning Dynamics Through Structured Representations
Saleh Nikooroo, Thomas Engel
While modern deep networks have demonstrated remarkable versatility, their training dynamics remain poorly understood--often driven more by empirical tweaks than architectural insi…
cs.LG2025
Cross-Model Semantics in Representation Learning
Saleh Nikooroo, Thomas Engel
The internal representations learned by deep networks are often sensitive to architecture-specific choices, raising questions about the stability, alignment, and transferability of…
cs.LG2025
Structured Transformations for Stable and Interpretable Neural Computation
Saleh Nikooroo, Thomas Engel
Despite their impressive performance, contemporary neural networks often lack structural safeguards that promote stable learning and interpretable behavior. In this work, we introd…