GenusSink achieves near-linear time approximate generalized Sinkhorn for bounded genus graphs via separator decompositions, computational geometry, and fast distance matrix operations.
Ot-transformer: a continuous-time transformer architecture with optimal transport regularization.arXiv preprint arXiv:2501.18793
3 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
3
Pith papers citing it
1
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
FLUID is a continuous-time transformer using Liquid Attention Networks to model attention as stable ODE solutions that interpolate between discrete SDPA and CT-RNNs, with an explicit sink gate and liquid hyper-connections for better information flow.
Replacing additive residual connections with a gated rank-1 delta update that interpolates identity, projection, and reflection slightly improves language modeling and downstream averages in reported 124M/353M runs.
citing papers explorer
-
Near-Linear Time Generalized Sinkhorn Algorithms for Bounded Genus Graphs
GenusSink achieves near-linear time approximate generalized Sinkhorn for bounded genus graphs via separator decompositions, computational geometry, and fast distance matrix operations.
-
FLUID: Continuous-Time Hyperconnected Sparse Transformer for Sink-Free Learning
FLUID is a continuous-time transformer using Liquid Attention Networks to model attention as stable ODE solutions that interpolate between discrete SDPA and CT-RNNs, with an explicit sink gate and liquid hyper-connections for better information flow.
-
Deep Delta Learning
Replacing additive residual connections with a gated rank-1 delta update that interpolates identity, projection, and reflection slightly improves language modeling and downstream averages in reported 124M/353M runs.