{"ID":5438564,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T01:40:09.565152011Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31026","arxiv_id":"2606.31026","title":"OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models","abstract":"We propose OTCache, a training-free framework for accelerating diffusion sampling via caching schedule prediction. Existing graph-based caching methods reduce redundant computation by optimizing shortest-path objectives, but rely on an additive independence assumption, which often breaks down in the low NFE regime. To address this issue, OTCache models caching schedules across inference budgets as a smooth evolution in policy space, inspired by Optimal Transport (OT). The framework consists of three stages: (1) obtaining a high-fidelity \\textbf{reference schedule} using a graph-based caching method under a conservative budget; (2) performing a lightweight anchor search under an extreme low-budget setting via Optuna optimization with an end-to-end perceptual objective; and (3) predicting schedules for target budgets via quantile interpolation between the reference and anchor policies using continuous warping representations. Experiments on FLUX.1 [dev], Qwen-Image, and HunyuanVideo show that OTCache achieves 4.5x, 4.7x, and 3.66x acceleration, respectively, while consistently improving generation fidelity over state-of-the-art caching baselines. This work provides a new perspective on accelerating diffusion models through Optimal-Transport-inspired schedule modeling. Code:https://github.com/UnicomAI/OTCache","short_abstract":"We propose OTCache, a training-free framework for accelerating diffusion sampling via caching schedule prediction. Existing graph-based caching methods reduce redundant computation by optimizing shortest-path objectives, but rely on an additive independence assumption, which often breaks down in the low NFE regime. To...","url_abs":"https://arxiv.org/abs/2606.31026","url_pdf":"https://arxiv.org/pdf/2606.31026v1","authors":"[\"Huanlin Gao\",\"Fang Zhao\",\"Qiang Hui\",\"Fuyuan Shi\",\"Shaoan Zhao\",\"Yantao Li\",\"Chao Tan\",\"Ting Lu\",\"Yuren You\",\"Kai Wang\",\"Shiguo Lian\"]","published":"2026-06-30T01:46:54Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":613757,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-01T01:17:58.482524686Z","DeletedAt":null,"paper_id":5438564,"paper_url":"https://arxiv.org/abs/2606.31026","paper_title":"OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models","repo_url":"https://github.com/UnicomAI/OTCache","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}