Controlla learns identity and attribute factors from multimodal inputs and aligns them with graph priors using graph-constrained optimal transport to enforce consistent attribute trajectories while preserving reference identity.
Gromov-wasserstein learning for graph matching and node embedding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Controlla: Learning Controllability via Graph-Constrained Latent Geometry
Controlla learns identity and attribute factors from multimodal inputs and aligns them with graph priors using graph-constrained optimal transport to enforce consistent attribute trajectories while preserving reference identity.