Lorentz 2DRNN introduces the first 2D hyperbolic NQS and outperforms Euclidean 2DRNN at the 2DTFIM critical point; 1D hyperbolic NQS also tested on reshaped 2D lattices.
arXiv preprint arXiv:2504.08912 (2025)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 3roles
method 1polarities
use method 1representative citing papers
HyFL-CLIP distills Euclidean CLIP alignment into hyperbolic space using cross-manifold similarity and Einstein midpoint aggregation to capture hierarchical part-whole relations, achieving up to 19.5% gains in long-text retrieval under perturbations.
Hyperbolic recurrent networks, especially a Lorentz-model RNN, reach lower variational ground-state energies than Euclidean RNN/GRU wavefunctions on 100-spin Heisenberg chains, with up to three times fewer parameters.
citing papers explorer
-
Two-dimensional Hyperbolic RNN Neural Quantum State
Lorentz 2DRNN introduces the first 2D hyperbolic NQS and outperforms Euclidean 2DRNN at the 2DTFIM critical point; 1D hyperbolic NQS also tested on reshaped 2D lattices.
-
HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding
HyFL-CLIP distills Euclidean CLIP alignment into hyperbolic space using cross-manifold similarity and Einstein midpoint aggregation to capture hierarchical part-whole relations, achieving up to 19.5% gains in long-text retrieval under perturbations.
-
New non-Euclidean neural quantum states from hyperbolic Lorentz recurrent architectures
Hyperbolic recurrent networks, especially a Lorentz-model RNN, reach lower variational ground-state energies than Euclidean RNN/GRU wavefunctions on 100-spin Heisenberg chains, with up to three times fewer parameters.