Answers are grounded in this paper and cite their sources.
Proposed framework reduces sampling cost by 25.5% in diffusion models, while enhancing quality metrics like FID and CLIP.
Diffusion models manifest evident benefits across diverse domains, yet their high sampling cost, requiring dozens of sequential model evaluations, remains a major limitation. Prior efforts mainly accelerate sampling via optimized solvers or distillation, which treat each query independently. In contrast, we reduce total number of steps by sharing early-stage sampling across semantically similar queries. To enable such efficiency gains without sacrificing quality, we propose SAGE, a semantic-aware shared sampling framework that integrates a shared sampling scheme for efficiency and a tailored training strategy for quality preservation. Extensive experiments show that SAGE reduces sampling cost by 25.5%, while improving generation quality with 5.0% lower FID, 5.4% higher CLIP, and 160% higher diversity over baselines.
No takes yet. Share an insight, caveat, or question.
Zhao et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: