{
  "id": 4028,
  "url": "https://arxiv.org/abs/2605.19729v3",
  "title": "LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models",
  "summary": "We demonstrate that in knowledge distillation for diffusion models, the teacher network's highly complex denoising process - stemming from its substantially larger capacity - poses a significant challenge for the student model to faithfully mimic. To address this problem, we propose a coarse-to-fine distillation framework with LInear FiTtingbased distillation (LIFT) and Piecewise Local Adaptive Coefficient Estimation (PLACE). First, LIFT decomposes the objective into a \"coarse\" alignment and a \"",
  "authors": "Hyunsoo Han, Sangyeop Yeo, Jaejun Yoo",
  "category": "research",
  "topics": "safety-alignment,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-19T12:03:53.000Z",
  "fetched_at": "2026-07-14T16:30:41.582Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4028",
  "original_url": "https://arxiv.org/abs/2605.19729v3",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}