Implicit Manifold-valued Diffusions (IMDs) are data-driven SDEs built from proximity graphs that converge in law to smooth manifold diffusions as sample count increases.
Laplacian eigenmaps for dimensionality reduction and data representation.Neural computation, 15(6):1373–1396
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5representative citing papers
LRD framework with Frenet, NRS, and GFMI metrics shows layer-wise structure in 31 models provides usable signal for model selection and pruning on MTEB tasks.
A spectral vision transformer achieves equitable or superior performance with fewer parameters than standard ViTs, CNNs, and other models by using spectral projections for tokenization in limited-data medical imaging.
SOMA estimates a local response manifold from early turns and adapts a small surrogate model via divergence-maximizing prompts and localized LoRA fine-tuning for efficient multi-turn serving.
VLMs possess a latent 3D scene topology subspace corresponding to Laplacian eigenmaps that can be causally shaped via Dirichlet energy regularization to improve spatial task performance by up to 12.1%.
citing papers explorer
-
Diffusion Processes on Implicit Manifolds
Implicit Manifold-valued Diffusions (IMDs) are data-driven SDEs built from proximity graphs that converge in law to smooth manifold diffusions as sample count increases.
-
Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs
LRD framework with Frenet, NRS, and GFMI metrics shows layer-wise structure in 31 models provides usable signal for model selection and pruning on MTEB tasks.
-
Spectral Vision Transformer for Efficient Tokenization with Limited Data
A spectral vision transformer achieves equitable or superior performance with fewer parameters than standard ViTs, CNNs, and other models by using spectral projections for tokenization in limited-data medical imaging.
-
SOMA: Efficient Multi-turn LLM Serving via Small Language Model
SOMA estimates a local response manifold from early turns and adapts a small surrogate model via divergence-maximizing prompts and localized LoRA fine-tuning for efficient multi-turn serving.
-
Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models
VLMs possess a latent 3D scene topology subspace corresponding to Laplacian eigenmaps that can be causally shaped via Dirichlet energy regularization to improve spatial task performance by up to 12.1%.