{"ID":2867306,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.19276","arxiv_id":"2509.19276","title":"A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Models","abstract":"Solving ill-posed inverse problems requires powerful and flexible priors. We propose leveraging pretrained latent diffusion models for this task through a new training-free approach, termed Diffusion-regularized Wasserstein Gradient Flow (DWGF). Specifically, we formulate the posterior sampling problem as a regularized Wasserstein gradient flow of the Kullback-Leibler divergence in the latent space. We demonstrate the performance of our method on standard benchmarks using StableDiffusion (Rombach et al., 2022) as the prior.","short_abstract":"Solving ill-posed inverse problems requires powerful and flexible priors. We propose leveraging pretrained latent diffusion models for this task through a new training-free approach, termed Diffusion-regularized Wasserstein Gradient Flow (DWGF). Specifically, we formulate the posterior sampling problem as a regularized...","url_abs":"https://arxiv.org/abs/2509.19276","url_pdf":"https://arxiv.org/pdf/2509.19276v1","authors":"[\"Tim Y. J. Wang\",\"O. Deniz Akyildiz\"]","published":"2025-09-23T17:41:43Z","proceeding":"stat.ML","tasks":"[\"stat.ML\",\"cs.LG\",\"stat.CO\"]","methods":"[\"Diffusion Model\"]","has_code":false}