paper-with-me

Papers

Stable Autonomous Flow Matching

2024-02-08 · Christopher Iliffe Sprague, Arne Elofsson, Hossein Azizpour

In contexts where data samples represent a physically stable state, it is often assumed that the data points represent the local minima of an energy landscape. In control theory, it is well-known that energy can serve as an effective Lyapunov function. Despite this, connections between control theory and generative models in the literature are sparse, even though there are several machine learning applications with physically stable data points. In this paper, we focus on such data and a recent class of deep generative models called flow matching. We apply tools of stochastic stability for time-independent systems to flow matching models. In doing so, we characterize the space of flow matching models that are amenable to this treatment, as well as draw connections to other control theory principles. We demonstrate our theoretical results on two examples.

📄 PDF Abstract BibTeX arXiv:2402.05774

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Learning Direct Control Policies with Flow Matching for Autonomous Driving

2026-05-14 · Marcello Ceresini, Federico Pirazzoli, Andrea Bertogalli, Lorenzo Cipelli 외 arxiv

We present a flow-matching planner for autonomous driving that directly outputs actionable control trajectories defined by acceleration and curvature profiles. The model is conditioned on a bird's-eye-view (BEV) raster o…

Autonomous Driving

Conditional Flow Matching for Continuous Anomaly Detection in Autonomous Driving on a Manifold-Aware Spectral Space

2026-02-19 · Antonio Guillen-Perez arxiv

Safety validation for Level 4 autonomous vehicles (AVs) is currently bottlenecked by the inability to scale the detection of rare, high-risk long-tail scenarios using traditional rule-based heuristics. We present Deep-Fl…

Autonomous VehiclesAutonomous DrivingAnomaly Detection

ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video

2024-07-13 · Han Ling, Quansen Sun

Perceiving and understanding 3D motion is a core technology in fields such as autonomous driving, robots, and motion prediction. This paper proposes a 3D motion perception method called ScaleFlow++ that is easy to genera…

Autonomous DrivingMotion Estimationmotion predictionOptical Flow Estimation+2

ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video

2024-09-16 · Han Ling, Yinghui Sun, Quansen Sun, yuhui Zheng

Perceiving and understanding 3D motion is a core technology in fields such as autonomous driving, robots, and motion prediction. This paper proposes a 3D motion perception method called ScaleFlow++ that is easy to genera…

Autonomous Drivingmotion predictionOptical Flow EstimationScene Flow Estimation+1

Beckmann Transport Models: From Autonomous Flows to One-Step Maps

2026-08-03 · Lee Cheuk-Kit, Florentin Coeurdoux, Peter Potaptchik, Yilun Du 외 arxiv

We propose an instantiation of flow matching that relies on a time-independent velocity field (an \emph{autonomous flow}) to exactly map between two distributions, so long as the target is singular, i.e.\ supported on a …