Beyond Uniform Local Isometry and Topology: FactoMap for Disentangled Representations
Many disentanglement methods represent generative factors using Euclidean product coordinates, although the underlying factor spaces may wrap, collapse, or have position-dependent geometry. We introduce factor-space structure, combining factor domains, generator-induced identifications, and position-dependent scales to distinguish topologically equivalent spaces with different factor geometries. We show that statistically independent factors need not be geometrically separable: hue and scale produce effects that grow at different rates, yielding anisotropy that no fixed rescaling removes. We p
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 84%mudler/LocalAI →
“Fuzzy title match (0.92): “Beyond Uniform Local Isometry and Topology: FactoMap for Dis” ≈ “mudler/LocalAI””
- FuzzyOverlapping authors or contributors · 62%microsoft/ML-For-Beginners →
“Shared author/contributor keys: gupta”
- LinkedLinked via arxiv author · 85%Sohini Gupta →
“Beyond Uniform Local Isometry and Topology: FactoMap for Disentangled Representations”
- LinkedLinked via arxiv author · 85%Bahareh Tolooshams →
“Beyond Uniform Local Isometry and Topology: FactoMap for Disentangled Representations”