A new discrete diffusion model for scene graph generation from text captures object-relation dependencies via hierarchical constraints and training-free conditioning, yielding better graph metrics and downstream image alignment than prior baselines.
Deep unsupervised learning using nonequilibrium thermodynamics
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
MSDDA derives a closed-form optimal reverse denoising distribution for multi-objective diffusion alignment that is exactly equivalent to step-level RL fine-tuning with no approximation error.
citing papers explorer
-
Dependency-Aware Discrete Diffusion for Scene Graph Generation
A new discrete diffusion model for scene graph generation from text captures object-relation dependencies via hierarchical constraints and training-free conditioning, yielding better graph metrics and downstream image alignment than prior baselines.
-
Step-level Denoising-time Diffusion Alignment with Multiple Objectives
MSDDA derives a closed-form optimal reverse denoising distribution for multi-objective diffusion alignment that is exactly equivalent to step-level RL fine-tuning with no approximation error.