{
  "id": 6783,
  "url": "https://arxiv.org/abs/2603.23903v1",
  "title": "Latent Bias Alignment for High-Fidelity Diffusion Inversion in Real-World Image Reconstruction and Manipulation",
  "summary": "Recent research has shown that text-to-image diffusion models are capable of generating high-quality images guided by text prompts. But can they be used to generate or approximate real-world images from the seed noise? This is known as the diffusion inversion problem, which serves as a fundamental building block for bridging diffusion models and real-world scenarios. However, existing diffusion inversion methods often suffer from low reconstruction quality or weak robustness. Two major challenge",
  "authors": "Weiming Chen, Qifan Liu, Siyi Liu, Yushun Tang, Yijia Wang, Zhihan Zhu et al.",
  "category": "research",
  "topics": "bias-fairness,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-25T03:44:21.000Z",
  "fetched_at": "2026-07-14T16:32:45.892Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6783",
  "original_url": "https://arxiv.org/abs/2603.23903v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}