{"ID":2860303,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04188","arxiv_id":"2510.04188","title":"Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers","abstract":"Diffusion Transformers offer state-of-the-art fidelity in image and video synthesis, but their iterative sampling process remains a major bottleneck due to the high cost of transformer forward passes at each timestep. To mitigate this, feature caching has emerged as a training-free acceleration technique that reuses or forecasts hidden representations. However, existing methods often apply a uniform caching strategy across all feature dimensions, ignoring their heterogeneous dynamic behaviors. Therefore, we adopt a new perspective by modeling hidden feature evolution as a mixture of ODEs across dimensions, and introduce HyCa, a Hybrid ODE solver inspired caching framework that applies dimension-wise caching strategies. HyCa achieves near-lossless acceleration across diverse domains and models, including 5.55 times speedup on FLUX, 5.56 times speedup on HunyuanVideo, 6.24 times speedup on Qwen-Image and Qwen-Image-Edit without retraining.","short_abstract":"Diffusion Transformers offer state-of-the-art fidelity in image and video synthesis, but their iterative sampling process remains a major bottleneck due to the high cost of transformer forward passes at each timestep. To mitigate this, feature caching has emerged as a training-free acceleration technique that reuses or...","url_abs":"https://arxiv.org/abs/2510.04188","url_pdf":"https://arxiv.org/pdf/2510.04188v1","authors":"[\"Shikang Zheng\",\"Guantao Chen\",\"Qinming Zhou\",\"Yuqi Lin\",\"Lixuan He\",\"Chang Zou\",\"Peiliang Cai\",\"Jiacheng Liu\",\"Linfeng Zhang\"]","published":"2025-10-05T13:01:08Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}