A training-free adaptive subspace projection method mitigates semantic collapsing in generative personalization by isolating and adjusting drift in a low-dimensional subspace using the stable pre-trained embedding as anchor.
Generate anything anywhere in any scene
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CV 3verdicts
UNVERDICTED 3roles
other 1polarities
unclear 1representative citing papers
SynMotion combines disentangled semantic embeddings, parameter-efficient motion adapters, and alternate subject-motion training on a new SPV dataset to improve motion customization in text-to-video and image-to-video generation.
SOW uses MLLMs and attention to selectively control unidirectional diffusion for pixel-level fidelity and contextual coherence in text-vision-to-image tasks.
citing papers explorer
-
Adaptive Subspace Projection for Generative Personalization
A training-free adaptive subspace projection method mitigates semantic collapsing in generative personalization by isolating and adjusting drift in a low-dimensional subspace using the stable pre-trained embedding as anchor.
-
SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation
SynMotion combines disentangled semantic embeddings, parameter-efficient motion adapters, and alternate subject-motion training on a new SPV dataset to improve motion customization in text-to-video and image-to-video generation.
-
SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation
SOW uses MLLMs and attention to selectively control unidirectional diffusion for pixel-level fidelity and contextual coherence in text-vision-to-image tasks.