Prompts can be split into separate roles for sampling design and recovery modeling in generative compressed sensing, with stable recovery bounds for matched prompts and an explicit penalty for mismatch, validated on Stable Diffusion.
Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
A novel identity connects reduced-model drift and diffusion to the conditional score of the finite-time transition density, turning calibration into a least-squares problem over stationary lagged pairs that preserves invariant statistics and dynamical correlations.
Pattern formation in trained diffusion models emerges from out-of-equilibrium phase transitions driven by instabilities in low-frequency denoising modes linked to data symmetries and architectural constraints.
LAMP adds a lagged temporal correction derived from second-order discretization to diffusion posterior samplers, yielding consistent gains over DiffPIR and DDRM on imaging tasks via a bias-variance trade-off.
citing papers explorer
-
Active Learning for Conditional Generative Compressed Sensing
Prompts can be split into separate roles for sampling design and recovery modeling in generative compressed sensing, with stable recovery bounds for matched prompts and an explicit penalty for mismatch, validated on Stable Diffusion.
-
Conditional Score-Based Modeling of Effective Langevin Dynamics
A novel identity connects reduced-model drift and diffusion to the conditional score of the finite-time transition density, turning calibration into a least-squares problem over stationary lagged pairs that preserves invariant statistics and dynamical correlations.
-
How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models
Pattern formation in trained diffusion models emerges from out-of-equilibrium phase transitions driven by instabilities in low-frequency denoising modes linked to data symmetries and architectural constraints.
-
Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration
LAMP adds a lagged temporal correction derived from second-order discretization to diffusion posterior samplers, yielding consistent gains over DiffPIR and DDRM on imaging tasks via a bias-variance trade-off.
- A Tutorial on Diffusion Theory: From Differential Equations to Diffusion Models
- VRAG: Learning World Models for Interactive Video Generation