الملخص
Recently, Drifting Models and Wasserstein Gradient Flows have attracted substantial attention because they move iterative distributional refinement to training and amortize it into a generator, enabling fast inference. However, existing formulations have been developed largely for continuous Euclidean domains, such as image spaces, where particles admit unconstrained additive updates. On constrained spaces, these updates can leave the valid domain or ignore its geometry, making them unsuitable targets for training. Recent work has adapted updates to these spaces, but has focused on particular fields or offered limited empirical comparison. We derive and compare several geometry-aware fields within a common training framework for one-step generators. We test the method on data with different structures and obtain competitive one-step results in each setting. The best-performing field varies by task, showing why the choice of objective matters in practice.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Li, D., Lee, C., Yoo, J., Gushchin, N., Eijkelboom, F., Moulines, E., Panov, M., Korotin, A., Hong, S., & Kim, J. (2026). One-Step Generation via Riemannian Wasserstein Gradient Flows. https://omanscience.com/ar/articles/one-step-generation-via-riemannian-wasserstein-gradient-flows
MLA 9
Li, David, et al. "One-Step Generation via Riemannian Wasserstein Gradient Flows." https://omanscience.com/ar/articles/one-step-generation-via-riemannian-wasserstein-gradient-flows.
شيكاغو (المؤلف–التاريخ)
Li, David, Chanhyuk Lee, Jaehoon Yoo, Nikita Gushchin, Floor Eijkelboom, Eric Moulines, Maxim Panov, Alexander Korotin, Seunghoon Hong, and Jinwoo Kim. 2026. "One-Step Generation via Riemannian Wasserstein Gradient Flows." https://omanscience.com/ar/articles/one-step-generation-via-riemannian-wasserstein-gradient-flows.
هارفارد
Li, D., Lee, C., Yoo, J., Gushchin, N., Eijkelboom, F., Moulines, E., Panov, M., Korotin, A., Hong, S. and Kim, J. (2026) 'One-Step Generation via Riemannian Wasserstein Gradient Flows', Available at: https://omanscience.com/ar/articles/one-step-generation-via-riemannian-wasserstein-gradient-flows.
فانكوفر
Li D, Lee C, Yoo J, Gushchin N, Eijkelboom F, Moulines E, et al. One-Step Generation via Riemannian Wasserstein Gradient Flows. https://omanscience.com/ar/articles/one-step-generation-via-riemannian-wasserstein-gradient-flows
IEEE
D. Li, C. Lee, J. Yoo, N. Gushchin, F. Eijkelboom, E. Moulines, M. Panov, A. Korotin, S. Hong, and J. Kim, "One-Step Generation via Riemannian Wasserstein Gradient Flows," https://omanscience.com/ar/articles/one-step-generation-via-riemannian-wasserstein-gradient-flows.