新的流匹配技术提高了生成模型的准确性和效率

报道来源 [14]

1. arXiv cs.AI TIER_1 English(EN) · Anita Yang, Ken-ichi Kawarabayashi, Yohan Jung · 2026-11-05 05:00

   面向谱图生成的约束保持流匹配

   arXiv:2611.05436v1 Announce Type: cross Abstract: Spectral graph generation models graphs through the eigenvalues and eigenvectors of their Laplacians, providing a compact and continuous alternative to direct graph construction. However, these eigensystems must retain the structu…

2. arXiv cs.LG TIER_1 English(EN) · Nicolas Tricard, Linzheng Wang, Jason Chen, Sili Deng · 2026-11-05 05:00

   FlowReconBench：稀疏传感器学习和经典流重构的准确性、校准和成本

   arXiv:2611.06912v1 Announce Type: cross Abstract: Reconstructing full flow fields from sparse sensors requires prior assumptions about unmeasured regions and physical variables. Yet it remains unclear when learned models outperform classical estimators and which aspects of their …

3. arXiv cs.LG TIER_1 English(EN) · Giuliano Galadini, Aurelio Uncini, Danilo Comminiello · 2026-11-05 05:00

   面向无投影物理信息流匹配的能量引导传输

   arXiv:2611.06711v1 Announce Type: new Abstract: Deep generative models, particularly Flow Matching frameworks, have emerged as powerful tools for synthesizing complex physical systems. However, standard architectures remain purely statistically driven and agnostic to the underlyi…

4. arXiv cs.LG TIER_1 English(EN) · Qiangwei Peng, Lezhi Chen, Peijie Zhou · 2026-11-02 05:00

   多尺度监督不平衡最优输运流匹配

   arXiv:2605.16529v2 Announce Type: replace Abstract: Unbalanced optimal transport (UOT) provides a principled framework for modeling single-cell transitions and birth-death dynamics, but its high computational cost limits scalability to large-scale datasets. Although single-cell d…

5. arXiv cs.AI TIER_1 English(EN) · Kunpeng Liu, Boshi Zhang, Keyou You · 2026-10-31 04:00

   AegisFlow：无需训练的非近视路径安全引导流匹配

   arXiv:2610.39825v1 Announce Type: new Abstract: Pretrained generative models, such as diffusion and flow matching models, have demonstrated exceptional capabilities in synthesizing high-quality data. However, steering their generative trajectories to satisfy strict constraints--s…

6. Hugging Face Daily Papers TIER_1 English(EN) · 2026-10-29 14:12

   Coupled Guidance for Flow Matching

   Guidance methods are essential tools for steering the generation process in diffusion models, improving the generalizability of stochastic robotic controllers and enabling high-quality controlled image synthesis. Despite strong parallels between flow-matching and diffusion, integ…

7. Hugging Face Daily Papers TIER_1 English(EN) · 2026-10-28 04:42

   NAGO：通过流匹配实现的噪声感知生成算子

   We introduce NAGO, a noise-aware generative operator for efficient sampling from invariant measures of stochastic partial differential equations (SPDEs) in function space. Our central idea is to treat the source measure as a design variable rather than a fixed Gaussian default. W…

8. arXiv cs.CV TIER_1 English(EN) · Xiao Liu, Kai Liu, Naiyang Guan, Hongliang Lu, Zhixin Wang, Zhikai Chen, Renjing Pei, Yulun Zhang · 2026-11-05 05:00

   通过轨迹感知缓存加速变分流模型

   arXiv:2605.16789v2 Announce Type: replace Abstract: Diffusion and rectified flow (RF) models generate high-fidelity images and videos, but their iterative velocity-field evaluations are computationally expensive. Existing caching methods accelerate sampling by skipping timesteps,…

9. arXiv cs.CV TIER_1 English(EN) · Junseo Bang, Daewon Choi, Dong Ju Mun, Se Young Chun · 2026-11-05 05:00

   FLINT：为流匹配逆问题耦合近端初始化和有界随机性

   arXiv:2611.05945v1 Announce Type: new Abstract: Flow matching models have emerged as a dominant paradigm for generative posterior sampling in imaging inverse problems. Existing solvers follow two distinct lines of work: trajectory-space methods, which refine sampling dynamics fro…

10. arXiv cs.CV TIER_1 English(EN) · Runmin Zhang, Linshan Li, Si-Yuan Cao, Zhu Yu, Lingyu Zhu, Huaqi Zhang, Hui-Liang Shen · 2026-11-05 05:00

    通过跨模态条件流匹配实现未对齐图像引导去噪

    arXiv:2611.06422v1 Announce Type: new Abstract: This work presents UGD-FM, a novel unaligned image guided denoising framework based on cross-modal conditional flow matching. Unlike previous approaches that assume spatially aligned inputs or only handle small-baseline rectified pa…

11. arXiv cs.CV TIER_1 English(EN) · Sevket Ege Yesilyurt, Figen S. Oktem · 2026-11-05 05:00

    Dual Flow: 联合图像-测量流用于逆问题

    arXiv:2611.05843v1 Announce Type: cross Abstract: Existing generative model-based approaches to linear inverse problems typically use the acquired noisy measurement to condition or guide sampling in the image domain. In this work, we introduce Dual Flow, a novel joint flow model …

12. arXiv stat.ML TIER_1 English(EN) · Soon Hoe Lim, Aditi Gupta, Michael W. Mahoney, N. Benjamin Erichson · 2026-11-02 05:00

    用于流匹配无回滚训练的粗粒化最优传输

    arXiv:2610.41269v1 Announce Type: new Abstract: Flow matching depends critically on the coupling used to pair source and target samples. Optimal transport (OT) couplings can reduce velocity conflict and straighten trajectories; but, in practice, challenges remain: the source come…

13. arXiv cs.CV TIER_1 English(EN) · Liangjing Shao, Wanhao Liu, Jinsong Lin, Zhiwei Fang, Hongliang Ren · 2026-11-02 05:00

    FlowMoDE：用于细节感知单目深度估计的粗粒度到细粒度流匹配

    arXiv:2610.41190v1 Announce Type: new Abstract: Monocular depth estimation is a fundamental capability for 3D spatial perception in robotic and intelligent systems. While data-driven discriminative methods have achieved compelling performance for monocular depth estimation, gener…

14. arXiv cs.CV TIER_1 English(EN) · Zhiqi Zhang, Xinhao Zhong, Yi Sun, Shuoyang Sun, Jiahui Wang, Bin Chen, Shu-Tao Xia, Xuan Wang · 2026-11-02 05:00

    差分向量擦除：流匹配模型的统一无训练概念擦除

    arXiv:2602.01089v2 Announce Type: replace Abstract: Text-to-image diffusion models have demonstrated remarkable capabilities in generating high-quality images, yet their tendency to reproduce undesirable concepts, such as NSFW content, copyrighted styles, or specific objects, pos…