Proposes diffeomorphic optimization for manifold-constrained problems in generative models via flow maps, with Lie-group extensions for protein design showing metric improvements.
Verifying the union of manifolds hypothesis for image data
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
VSM modulates the score Jacobian using variance guidance to reduce hallucinations in diffusion models by up to 25% on synthetic and real datasets while preserving fidelity and diversity.
The paper establishes a correspondence between Signal Temporal Logic and stratification theory, allowing STL formulas to be viewed as stratifications of space-time and applied to analyze DRL embedding spaces via robustness rewards.
citing papers explorer
-
Diffeomorphic Optimization
Proposes diffeomorphic optimization for manifold-constrained problems in generative models via flow maps, with Lie-group extensions for protein design showing metric improvements.
-
Score-Control for Hallucination Reduction in Diffusion Models
VSM modulates the score Jacobian using variance guidance to reduce hallucinations in diffusion models by up to 25% on synthetic and real datasets while preserving fidelity and diversity.
-
Stratifying Reinforcement Learning with Signal Temporal Logic
The paper establishes a correspondence between Signal Temporal Logic and stratification theory, allowing STL formulas to be viewed as stratifications of space-time and applied to analyze DRL embedding spaces via robustness rewards.