{
  "id": "diffusion-input-perturbation",
  "title": "Input Perturbation Reduces Exposure Bias in Diffusion Models",
  "authors": [
    {
      "given": "Mang",
      "family": "Ning"
    },
    {
      "given": "Enver",
      "family": "Sangineto"
    },
    {
      "given": "Angelo",
      "family": "Porrello"
    },
    {
      "given": "Simone",
      "family": "Calderara"
    },
    {
      "given": "Rita",
      "family": "Cucchiara"
    }
  ],
  "year": 2023,
  "venue": "ICML 2023",
  "paper_url": "https://proceedings.mlr.press/v202/ning23a.html",
  "pdf_url": "https://proceedings.mlr.press/v202/ning23a/ning23a.pdf",
  "summary": "Studies accumulated sampling errors in diffusion models and trains with perturbed inputs to simulate inference-time prediction errors.",
  "connection": "Addresses the same training–sampling mismatch through input perturbation, providing a comparison with scheduled sampling on model-generated states.",
  "bibtex_type": "inproceedings",
  "citation_key": "pmlr-v202-ning23a",
  "source_urls": [
    "https://proceedings.mlr.press/v202/ning23a.html"
  ],
  "updated_at": "2026-11-10",
  "record_url": "https://yuntiandeng.com/research/papers/diffusion-input-perturbation/"
}