{"ID":2850607,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.21366","arxiv_id":"2510.21366","title":"BADiff: Bandwidth Adaptive Diffusion Model","abstract":"In this work, we propose a novel framework to enable diffusion models to adapt their generation quality based on real-time network bandwidth constraints. Traditional diffusion models produce high-fidelity images by performing a fixed number of denoising steps, regardless of downstream transmission limitations. However, in practical cloud-to-device scenarios, limited bandwidth often necessitates heavy compression, leading to loss of fine textures and wasted computation. To address this, we introduce a joint end-to-end training strategy where the diffusion model is conditioned on a target quality level derived from the available bandwidth. During training, the model learns to adaptively modulate the denoising process, enabling early-stop sampling that maintains perceptual quality appropriate to the target transmission condition. Our method requires minimal architectural changes and leverages a lightweight quality embedding to guide the denoising trajectory. Experimental results demonstrate that our approach significantly improves the visual fidelity of bandwidth-adapted generations compared to naive early-stopping, offering a promising solution for efficient image delivery in bandwidth-constrained environments. Code is available at: https://github.com/xzhang9308/BADiff.","short_abstract":"In this work, we propose a novel framework to enable diffusion models to adapt their generation quality based on real-time network bandwidth constraints. Traditional diffusion models produce high-fidelity images by performing a fixed number of denoising steps, regardless of downstream transmission limitations. However,...","url_abs":"https://arxiv.org/abs/2510.21366","url_pdf":"https://arxiv.org/pdf/2510.21366v3","authors":"[\"Xi Zhang\",\"Hanwei Zhu\",\"Yan Zhong\",\"Jiamang Wang\",\"Weisi Lin\"]","published":"2025-10-24T11:50:03Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":607820,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2850607,"paper_url":"https://arxiv.org/abs/2510.21366","paper_title":"BADiff: Bandwidth Adaptive Diffusion Model","repo_url":"https://github.com/xzhang9308/BADiff","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}