Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Université Côte d'Azur, Inria Université Côte d'Azur, Inria
2
0
2
A single sentence can now capture a document's nuanced thematic progression, revealing how speakers shift topics within conversations.
Ditching entropic regularization in Gromov-Wasserstein unlocks consistent recovery of SBM connectivity and latent clusters, but you'll need sparsity-promoting regularization for reliable finite-sample model selection.