VINS-120K supplies the first large-scale set of instruction-image-edited-image triplets at ultra-high resolution together with an adaptation strategy that improves detail synthesis.
Emu edit: Precise image editing via recognition and gen- eration tasks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
SOLACE improves text-to-image generation by using intrinsic self-confidence rewards from noise reconstruction accuracy during reinforcement learning post-training without external supervision.
HierEdit enables efficient 4K image editing via low-resolution proxy localization followed by hierarchical local-window diffusion that reuses unaltered regions as conditioning.
citing papers explorer
-
VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset
VINS-120K supplies the first large-scale set of instruction-image-edited-image triplets at ultra-high resolution together with an adaptation strategy that improves detail synthesis.
-
Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards
SOLACE improves text-to-image generation by using intrinsic self-confidence rewards from noise reconstruction accuracy during reinforcement learning post-training without external supervision.
-
HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing
HierEdit enables efficient 4K image editing via low-resolution proxy localization followed by hierarchical local-window diffusion that reuses unaltered regions as conditioning.