A masking-augmented diffusion objective plus pause-token inference scaling modestly improves instruction adherence and source preservation for OmniGen-based image editing.
Got: Unleashing reasoning capability of multimodal large language model for visual generation and editing, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
MADI: Masking-Augmented Diffusion with Inference-Time Scaling for Visual Editing
A masking-augmented diffusion objective plus pause-token inference scaling modestly improves instruction adherence and source preservation for OmniGen-based image editing.