Embedding norms in contrastive models encode semantic properties via optimization dynamics under scale-invariant losses.
The double-ellipsoid geometry of clip.arXiv preprint arXiv:2411.14517
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
A spiked signal-plus-noise model yields separation ratios that partition multimodal problems into four regimes where alignment, prediction, both, or neither succeed.
HEART performs Kent-aware geodesic transformations on hyperspherical text embeddings to enable precise, training-free control in text-to-image diffusion models.
A consistency-regularized Euclidean-Wasserstein-2 gradient flow performs joint posterior sampling and prompt optimization in latent space for efficient low-NFE inverse problem solving with diffusion models.
citing papers explorer
-
Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
Embedding norms in contrastive models encode semantic properties via optimization dynamics under scale-invariant losses.
-
HEART: Hyperspherical Embedding Alignment via Kent-Representation Traversal in Diffusion Models
HEART performs Kent-aware geodesic transformations on hyperspherical text embeddings to enable precise, training-free control in text-to-image diffusion models.
-
Consistency Regularised Gradient Flows for Inverse Problems
A consistency-regularized Euclidean-Wasserstein-2 gradient flow performs joint posterior sampling and prompt optimization in latent space for efficient low-NFE inverse problem solving with diffusion models.