{"type":"ScholarlyArticle","title":"One Flow Fits All! A Scale-Aware Generative Framework for Diverse Data","authors":[{"name":"Hubin Cao","slug":"hubin-cao","given":"Hubin","family":"Cao","affiliation":""},{"name":"Jun Ma","slug":"jun-ma","given":"Jun","family":"Ma","affiliation":""},{"name":"Yusupu Ainiwaer","slug":"yusupu-ainiwaer","given":"Yusupu","family":"Ainiwaer","affiliation":""},{"name":"Hanquan Zhang","slug":"hanquan-zhang","given":"Hanquan","family":"Zhang","affiliation":""},{"name":"Yanjun Qin","slug":"yanjun-qin","given":"Yanjun","family":"Qin","affiliation":""},{"name":"Zixuan Wang","slug":"zixuan-wang","given":"Zixuan","family":"Wang","affiliation":""},{"name":"Xiaoming Tao","slug":"xiaoming-tao","given":"Xiaoming","family":"Tao","affiliation":""}],"abstract":"Real-world systems increasingly require coherent reasoning and generation over diverse data modalities simultaneously. Current generative frameworks rely on complex, multi-stage training, resulting in low efficiency due to iterative inference and high computational cost. They also struggle with unified multimodal representation, failing to balance fine-grained details with global structures and long-term dependencies, which limits generative quality and practical usability. To overcome these limitations, we introduce the Inverse Heat Mean Flow (IHMF), a general-purpose solver that is compatible with a wide range of model backbones. Without requiring pre-training, IHMF directly learns an average velocity field through an inverse heat formul ation. By exploiting the inherent scale-space properties of the inverse heat process, IHMF explicitly decomposes multi-scale complexities, thereby simplifying trajectory learning and enabling adaptive topological alignment. Extensive experiments show that IHMF achieves a competitive performance with state-of-the-art methods, providing a robust and unified mathematical framework for various generative tasks. The code is publicly available at https://github.com/CHBonline/IHMF.","doi":"10.24963/ijcai.2026/106","url":"https://ijcai.org/proceedings/2026/106","pdf":"https://ijcai.org/proceedings/2026/0106.pdf","markdown":"https://ijcai.org/proceedings/2026/106.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/106","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":106,"pages":{"first":944,"last":952},"keywords":["Computer Vision: Image and video synthesis and generation"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}