Introduces a training-free inference-time method for aesthetic refinement in unconditional diffusion models using degradation concept vectors, bottleneck patching, and classifier-free guidance to steer away from degraded outputs.
Unsupervised discovery of semantic latent directions in diffusion models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Introduces 9 synthetic annotation tasks and benchmarks for behavioral cloning, finding hierarchical skill learning, scaling benefits, effective multi-task pretraining, and shared internal representations of task phases and mistakes.
Semantic similarity between texts is measured by the Jeffreys divergence between the image distributions induced by conditioning a diffusion model on each text, computed via Monte-Carlo sampling of the reverse-time SDEs.
citing papers explorer
-
Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models
Introduces a training-free inference-time method for aesthetic refinement in unconditional diffusion models using degradation concept vectors, bottleneck patching, and classifier-free guidance to steer away from degraded outputs.
-
A Systematic Study of Behavioral Cloning for Scientific Data Annotation
Introduces 9 synthetic annotation tasks and benchmarks for behavioral cloning, finding hierarchical skill learning, scaling benefits, effective multi-task pretraining, and shared internal representations of task phases and mistakes.