中文
相关论文

相关论文: Coreset-Induced Conditional Velocity Flow Matching

200 篇论文

Conditional Flow Matching (CFM), a simulation-free method for training continuous normalizing flows, provides an efficient alternative to diffusion models for key tasks like image and video generation. The performance of CFM in solving…

机器学习 · 计算机科学 2026-03-17 Aram Davtyan , Leello Tadesse Dadi , Volkan Cevher , Paolo Favaro

Forecasting conditional stochastic nonlinear dynamical systems is a fundamental challenge repeatedly encountered across the biological and physical sciences. While flow-based models can impressively predict the temporal evolution of…

机器学习 · 计算机科学 2025-04-02 Adam P. Generale , Andreas E. Robertson , Surya R. Kalidindi

Conditional flow matching (CFM) has emerged as a powerful framework for training continuous normalizing flows due to its computational efficiency and effectiveness. However, standard CFM often produces paths that deviate significantly from…

Flow matching (FM) is a family of training algorithms for fitting continuous normalizing flows (CNFs). Conditional flow matching (CFM) exploits the fact that the marginal vector field of a CNF can be learned by fitting least-squares…

机器学习 · 统计学 2025-02-04 Ganchao Wei , Li Ma

Generative models excel at synthesizing high-fidelity samples from complex data distributions, but they often violate hard constraints arising from physical laws or task specifications. A common remedy is to project intermediate samples…

机器学习 · 计算机科学 2025-09-30 Jinhao Liang , Yixuan Sun , Anirban Samaddar , Sandeep Madireddy , Ferdinando Fioretto

Flow matching models have shown great potential in image generation tasks among probabilistic generative models. However, most flow matching models in the literature do not explicitly utilize the underlying clustering structure in the…

计算机视觉与模式识别 · 计算机科学 2025-10-09 Anirban Samaddar , Yixuan Sun , Viktor Nilsson , Sandeep Madireddy

Granular flows govern many natural and industrial processes, yet their interior kinematics and mechanics remain largely unobservable, as experiments access only boundaries or free surfaces. Conventional numerical simulations are…

计算工程、金融与科学 · 计算机科学 2026-05-26 Xuyang Li , Rui Li , Teng Man , Yimin Lu

Standard flow matching scales well but typically relies on an unstructured source distribution, limiting its ability to learn interpretable latent structure. Latent-variable models, by contrast, capture structure but often sacrifice…

机器学习 · 计算机科学 2026-05-11 Xavier Sumba , Carles Balsells-Rodas , Yingzhen Li

Continuous normalizing flows (CNFs) are an attractive generative modeling technique, but they have been held back by limitations in their simulation-based maximum likelihood training. We introduce the generalized conditional flow matching…

The goal of this paper is to provide a new perspective on speech modeling by incorporating perceptual invariances such as amplitude scaling and temporal shifts. Conventional generative formulations often treat each dataset sample as a fixed…

音频与语音处理 · 电气工程与系统科学 2025-12-24 Doyeop Kwak , Youngjoon Jang , Joon Son Chung

Visually-guided acoustic highlighting seeks to rebalance audio in alignment with the accompanying video, creating a coherent audio-visual experience. While visual saliency and enhancement have been widely studied, acoustic highlighting…

音频与语音处理 · 电气工程与系统科学 2026-02-05 Hugo Malard , Gael Le Lan , Daniel Wong , David Lou Alon , Yi-Chiao Wu , Sanjeel Parekh

High-fidelity Monte Carlo simulations and complex inverse problems, such as mapping smeared experimental observations to ground-truth states, are computationally intensive yet essential for robust data analysis. Conditional Flow Matching…

机器学习 · 计算机科学 2026-04-03 Zeyu Xia , Tyler Kim , Trevor Reed , Judy Fox , Geoffrey Fox , Adam Szczepaniak

Conditional flow matching (CFM) stands out as an efficient, simulation-free approach for training flow-based generative models, achieving remarkable performance for data generation. However, CFM is insufficient to ensure accuracy in…

机器学习 · 计算机科学 2026-02-03 Yuhao Huang , Taos Transue , Shih-Hsin Wang , William Feldman , Hong Zhang , Bao Wang

This study presents a conditional flow matching framework for solving physics-constrained Bayesian inverse problems. In this setting, samples from the joint distribution of inferred variables and measurements are assumed available, while…

Daily or weekly cone-beam computed tomography (CBCT) is employed in image-guided radiotherapy (IGRT) for precise patient alignment. However, its clinical utility in quantitative tasks is hindered by severe artifacts and inaccurate Hounsfeld…

医学物理 · 物理学 2026-03-09 Junbo Peng , Huiqiao Xie , Tonghe Wang , Xiangyang Tang , Xiaofeng Yang

Flow matching has recently emerged as a powerful alternative to diffusion models, providing a continuous-time formulation for generative modeling and representation learning. Yet, we show that this framework suffers from a fundamental…

机器学习 · 计算机科学 2025-09-26 Weili Zeng , Yichao Yan

We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present the notion of Flow Matching (FM), a simulation-free approach for…

机器学习 · 计算机科学 2023-02-09 Yaron Lipman , Ricky T. Q. Chen , Heli Ben-Hamu , Maximilian Nickel , Matt Le

Flow matching (FM) learns vector fields by regressing stochastic velocity targets along intermediate distributions $p_t$. We identify a geometric optimization bottleneck in this regression problem: when the covariance $\Sigma_t$ of $p_t$ is…

机器学习 · 计算机科学 2026-05-14 Shadab Ahamed , Eshed Gal , Md Shahriar Rahim Siddiqui , Simon Ghyselincks , Moshe Eliasof , Eldad Haber

Continuous normalizing flows (CNFs) learn an ordinary differential equation to transform prior samples into data. Flow matching (FM) has recently emerged as a simulation-free approach for training CNFs by regressing a velocity model towards…

机器学习 · 统计学 2024-05-28 Tianyu Xie , Yu Zhu , Longlin Yu , Tong Yang , Ziheng Cheng , Shiyue Zhang , Xiangyu Zhang , Cheng Zhang

Normalizing flows are a class of deep generative models that are especially interesting for modeling probability distributions in physics, where the exact likelihood of flows allows reweighting to known target energy functions and computing…

机器学习 · 统计学 2023-11-27 Leon Klein , Andreas Krämer , Frank Noé
‹ 上一页 1 2 3 10 下一页 ›