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.
Diffusers: State-of-the-art diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
VAE-LFA suppresses semantic drift in multi-turn DiT image editing by low-pass filtering latent discrepancies and aligning low-frequency components to an EMA of previous rounds in VAE space.
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.
-
Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space
VAE-LFA suppresses semantic drift in multi-turn DiT image editing by low-pass filtering latent discrepancies and aligning low-frequency components to an EMA of previous rounds in VAE space.