Uni-AdGen uses a unified autoregressive framework with foreground perception, instruction tuning, and coarse-to-fine preference modules to generate personalized image-text ads from noisy user behaviors, outperforming baselines on a new PAd1M dataset.
Enhancing prompt following with visual control through training-free mask-guided diffu- sion
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
COLLAR introduces a training-free cascaded refinement framework with CSSA and CFI modules to improve object-level control and fidelity in diffusion transformer conditional generation.
citing papers explorer
-
Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models
Uni-AdGen uses a unified autoregressive framework with foreground perception, instruction tuning, and coarse-to-fine preference modules to generate personalized image-text ads from noisy user behaviors, outperforming baselines on a new PAd1M dataset.
-
COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional Generation
COLLAR introduces a training-free cascaded refinement framework with CSSA and CFI modules to improve object-level control and fidelity in diffusion transformer conditional generation.