arXiv Machine Learning
Is Flow Matching Just Trajectory Replay for Sequential Data?
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Oct 3
Variational Streaming Flow: Probabilistic Forecasting in Physical Time
Variational Streaming Flow (VSF) extends the efficient Streaming Flow (SF) framework by learning a latent distribution conditioned on system dynamics, enabling probabilistic forecasting in physical time. Unlike SF’s deterministic velocity field, VSF produces multiple plausible future trajectories, improving predictive accuracy and distributional fidelity across deterministic and stochastic dynamical systems. The method supports long‑horizon rollouts over 1,000 steps, handles bifurcating dynamics, and can be integrated as a plug‑and‑play predictor into Joint‑Embedding Predictive Architecture (JEPA) world models to enhance navigation, motion planning, and manipulation tasks.
arXiv Machine Learning
Jun 5
Multimarginal flow matching with optimal transport potentials
arXiv:2606. 05327v1 Announce Type: new Abstract: Flow matching (FM) has emerged as a powerful framework for learning dynamic transport maps between two empirical distributions.
arXiv AI
Sep 2
Training-Free Refinement of Flow Matching with Divergence-based Sampling
The paper introduces Flow Divergence Sampler (FDS), a training‑free method that refines intermediate states in flow‑matching models by using the divergence of the marginal velocity field to detect and correct misguidance toward low‑density regions. FDS operates during inference, requires no additional training, and can be applied as a plug‑and‑play module with standard solvers and existing flow backbones. Experiments show that FDS consistently improves fidelity in tasks such as text‑to‑image synthesis and inverse problems.
arXiv Machine Learning
Sep 30
Learning Continuous Patient Trajectories from Electronic Health Records
arXiv:2609.36144v1 Announce Type: new Abstract: Electronic health records provide irregular observations of latent patient states that evolve continuously over time. Recent autoregressive models cond...
Hugging Face Trending Papers
3d ago
Deterministic Prediction as Global Velocity: Flow Matching for Probabilistic Time-Series Forecast
The paper introduces DV-Flow, a flow‑matching framework that treats deterministic prediction as a parallel velocity component instead of embedding it within the generative process. This design stabilizes end‑to‑end training and unifies several existing methods as special cases, enabling direct comparison. Experiments on six real‑world datasets show that DV‑Flow consistently outperforms strong baselines in probabilistic time‑series forecasting.
arXiv Machine Learning
1d ago
PathFM: Fast Generative Forecasting of Multivariate Trajectories
arXiv:2610.22358v1 Announce Type: new Abstract: Time series foundation models are becoming increasingly popular for general-purpose forecasting. However, most leading models predict marginal quantile...