Home Knowledge Base Generative Flow Field

Generative Flow Field

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

3D Underwater Path Planning via Generative Flow Field Surrogates

arXiv:2606.06077v1 Announce Type: new Abstract: Autonomous underwater vehicle (AUV) launch and recovery (LAR) into the hull of an advancing host platform requires traversal of a complex, three-dimensional propeller wake whose hydrodynamic structure cannot be characterised by a uniform current model. High-fidelity Reynolds-Averaged Navier-Stokes (RANS) Computational Fluid Dynamics (CFD) simulations resolve this structure with sufficient accuracy for path planning, but their computational cost...

arXiv CS 5d ago

Unfolding Generative Flows with Koopman Operators: Trajectory-Preserving Linearization

Announce Type: replace Abstract: Continuous Normalizing Flows (CNFs) enable elegant generative modeling but remain bottlenecked by their iterative nature requiring costly sampling and lacking interpretability of the intermediate states. Recent approaches accelerate sampling by straightening trajectories or distilling endpoints, yet they treat the original generative process as a black box, discarding the teacher's intermediate dynamics. We propose a fundamentally different perspective:...

arXiv CS 9d ago

Scale-Adaptive Generative Flows for Multiscale Scientific Data

arXiv:2509.02971v2 Announce Type: replace-cross Abstract: Flow-based generative models can face numerical challenges on scientific data with multiscale Fourier spectra, often producing large errors at fine scales. We approach this problem within the flow matching and stochastic interpolants framework, through the principled design of noise distributions and interpolation schedules. Working in function space ensures that the generative model remains well defined as the resolution is refined;...

arXiv CS 5d ago

A Hybrid Generative Reduced-Order Model for the Minimal Flow Unit

Announce Type: new Abstract: A data-driven reduced-order modelling framework is proposed for wall-bounded turbulent flows to forecast the intermittent near-wall dynamics over extended time horizons from sparse sensor measurements. The approach combines a $\beta$-VAE-GAN, which compresses high-dimensional flow fields into a low-dimensional latent space, with a sensor-conditioned Transformer that forecasts the evolution of the latent variables. The temporal module employs Easy Attention, a...

arXiv Physics 1d ago

Latent Diffusion Policy: Shaping Latent Spaces for Diffusion-Based Robotic Manipulation

Announce Type: new Abstract: Diffusion-based visuomotor policies operating directly in raw action spaces conflate scene comprehension with trajectory generation within a single denoising process. The resulting velocity field must simultaneously encode scene information and generate precise trajectories, increasing learning complexity and limiting performance on tasks demanding precise temporal coordination across multiple arms. To simplify this joint learning problem, we introduce Latent...

arXiv CS 1d ago

A Kinetic Energy Perspective of Flow Matching

arXiv:2602.07928v2 Announce Type: replace Abstract: Flow-based generative models can be viewed through a physics lens: sampling transports a particle from noise to data by integrating a learned velocity field, and each sample corresponds to a trajectory with its own dynamical effort. Motivated by classical mechanics, we introduce Kinetic Path Energy (KPE), an action-like, per-sample diagnostic that measures the accumulated kinetic effort along an ordinary differential equation (ODE)...

arXiv CS 9d ago

OMP: One-step Meanflow Policy with Directional Alignment

arXiv:2512.19347v3 Announce Type: replace Abstract: Robot manipulation has increasingly adopted data-driven generative policy frameworks, yet the field faces a persistent trade-off: diffusion models suffer from high inference latency, while flow-based methods often require complex architectural constraints. Although in image generation domain, the MeanFlow paradigm offers a path to single-step inference, its direct application to robotics is impeded by critical theoretical pathologies,...

arXiv CS 7d ago

STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation

arXiv:2606.07036v1 Announce Type: new Abstract: Synthetic histopathology image generation addresses critical challenges in computational pathology, including patient privacy and the growing need for large-scale training data for foundation models. Latent diffusion models have dominated the image generation domain, with recent works emphasizing that the choice of latent space is critical to the quality of generated images. Existing state-of-the-art generative models in histopathology use...

arXiv CS 2d ago

How nonlinear spectral back transfer limits the temporal coherency of zonal modes?

arXiv:2604.03421v2 Announce Type: replace Abstract: Zonal modes are central to magnetic confinement because their radial shears regulate turbulence and transport. While the generation of these flows is well understood, the mechanisms limiting their persistence in collisionless regimes remain unresolved. In this paper, we demonstrate that nonlinear spectral back-transfer of free energy from zonal modes to turbulence sets the fundamental limit on the temporal coherency of the shearing field.

arXiv Physics 5d ago

Drifting Models for Surrogate Flow Modeling

arXiv:2606.07481v1 Announce Type: new Abstract: While Computational Fluid Dynamics (CFD) provides high-fidelity flow fields for optimizing indoor environments, its computational cost limits rapid exploration. To solve this problem generative surrogates offer better distribution modeling than deterministic networks, but iterative sampling is slow. To enable high-quality, single-pass generation, we adapt the novel generative drifting framework to fluid mechanics.

arXiv CS 2d ago