GDMD replaces raw-sample rewards with distillation-gradient rewards in RL-guided diffusion distillation, yielding 4-step models that surpass their multi-step teachers on GenEval and human preference metrics.
Advances in neural information processing systems35, 36479–36494 (2022)
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
MULTI uses two-stage textual inversion to disentangle camera lens, sensor, view, and domain factors for novel image generation, supporting dataset extension and ControlNet modifications on the new DF-RICO benchmark.
FluSplat trains a model with geometric alignment constraints on multi-view edits to produce consistent 3D scene edits from sparse views in a single forward pass without test-time optimization.
The paper presents the first generative photomosaic framework that synthesizes tiles via structure-aligned diffusion models and few-shot personalization instead of color-based matching from large tile collections.