3 citations · 5 across the 9 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Functional compatibility as a determinant of persistent neural learning
Hossein Javidnia
Neural networks can acquire new capabilities while damaging existing ones, but what determines whether new learning persists remains unclear. We identify functional compatibility,…
cs.LG2026
Semantic Sections: An Atlas-Native Feature Ontology for Obstructed Representation Spaces
Hossein Javidnia
Recent interpretability work often treats a feature as a single global direction, dictionary atom, or latent coordinate shared across contexts. We argue that this ontology can fail…
cs.LG2026
A Gauge Theory of Superposition: Toward a Sheaf-Theoretic Atlas of Neural Representations
Hossein Javidnia
We develop a discrete gauge-theoretic framework for superposition in large language models (LLMs) that replaces the single-global-dictionary premise with a sheaf-theoretic atlas of…