Conservative Flows: A New Paradigm of Generative Models

2026-05-07 · Eshed Gal, Md Shahriar Rahim Siddiqui, Moshe Eliasof, Eldad Haber arxiv

Modern generative modeling is dominated by transport from a noise prior to data. We propose an alternative paradigm in which generation is performed by a discrete stochastic dynamics that leaves the data distribution invariant, initialized from data-supported states rather than from noise. The framework can utilize any pretrained flow model. We develop two probability-preserving sampling mechanisms, a corrected Langevin dynamics with a Metropolis adjustment and a predictor-corrector flow, that operate directly on existing checkpoints. We validate the framework on a synthetic Swiss-roll target, ImageNet-256 and Oxford Flowers-102, where our samplers consistently improve over the original generation procedures.

📄 PDF Abstract BibTeX arXiv:2605.06905

Code (0)

등록된 구현이 없습니다.

Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows

2022-11-20 · Dmitriy Akimov, Vladislav Kurenkov, Alexander Nikulin, Denis Tarasov 외

Offline reinforcement learning aims to train a policy on a pre-recorded and fixed dataset without any additional environment interactions. There are two major challenges in this setting: (1) extrapolation error caused by…

Offline RL reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach

2023-10-10 · NeurIPS 2023 11 · Kai Zhao, Qiyu Kang, Yang song, Rui She 외

Graph neural networks (GNNs) are vulnerable to adversarial perturbations, including those that affect both node features and graph topology. This paper investigates GNNs derived from diverse neural flows, concentrating o…

Adversarial Robustness

Path differentiability of ODE flows

2022-01-11 · Swann Marx, Edouard Pauwels

We consider flows of ordinary differential equations (ODEs) driven by path differentiable vector fields. Path differentiable functions constitute a proper subclass of Lipschitz functions which admit conservative gradient…

Time-changed normalizing flows for accurate SDE modeling

2023-12-22 · Naoufal El Bekri, Lucas Drumetz, Franck Vermet

The generative paradigm has become increasingly important in machine learning and deep learning models. Among popular generative models are normalizing flows, which enable exact likelihood estimation by transforming a ba…

Gaussian Processes Time Series

FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching

2025-05-26 · Ziqian Wang, Zikai Liu, Xinfa Zhu, Yike Zhu 외

Generative models have excelled in audio tasks using approaches such as language models, diffusion, and flow matching. However, existing generative approaches for speech enhancement (SE) face notable challenges: language…

Quantization Speech Enhancement