Hugging Face Trending Papers

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

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.

By Hans Hao-Hsun Hsu, Minseon Gwak, Soon Hoe Lim, Pan Li, N. Benjamin Erichson

rag diffusion robotics

arXiv Machine Learning

Jun 2

Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching

arXiv:2605. 00941v4 Announce Type: replace Abstract: Flow matching has become a leading framework for generative modeling, but quantifying the uncertainty of its samples remains an open problem.

By Jiarui Xing, Song Wang, Jian Wang

diffusion

arXiv AI

Oct 2

ProtoFlow: Prototype-Guided Flow Matching for Multivariate Time Series Forecasting

ProtoFlow is a new multivariate time series forecasting framework that combines vector‑quantized autoencoding with prototype‑guided flow matching. It maps sequences into a discrete latent space, constructs a structured prior from the learned VQ codebook, and trains a DiT‑based rectified flow to transport samples from this prior to future latent representations conditioned on past observations. By replacing generic Gaussian noise with a learned prototype prior, ProtoFlow eliminates autoregressive rollout mismatch and achieves faster training convergence while delivering superior forecasting performance on benchmark datasets.

By Shibo Feng, Wanjin Feng, Yang Qiu, Deheng Ye, Peilin Zhao, Chunyan Miao

diffusion efficiency benchmarks safety

arXiv Machine Learning

Jul 14

CoGenCast: A Coupled Autoregressive-Flow Generative Framework for Time Series Forecasting

arXiv:2602. 03564v2 Announce Type: replace Abstract: Time series forecasting can be viewed as a generative problem that requires both semantic understanding over contextual conditions and stochastic modeling of continuous temporal dynamics.

By Mingyue Cheng, Yaguo Liu, Daoyu Wang, Xiaoyu Tao, Qi Liu

llms diffusion multimodal benchmarks

arXiv AI

Oct 7

SDFlow: Similarity-Driven Flow Matching for Time Series Generation

arXiv:2605.05736v3 Announce Type: replace Abstract: Vector quantization (VQ) with autoregressive (AR) token modeling is a widely adopted and highly competitive paradigm for time-series generation. Ho...

By Wei Li, Shibo Feng, Pengcheng Wu, Xingyu Gao, Min Wu, Peilin Zhao

diffusion efficiency benchmarks safety

arXiv Machine Learning

23h 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...

By Jiachen Yao, Xiyuan Zhang, Annan Yu, Boran Han, Abdul Fatir Ansari, Shuai Zhang, Michael Bohlke-Schneider, Bernie Wang

diffusion benchmarks

arXiv AI

Jul 17

Native Extrapolation Awareness in Flow-Based Conditional Generation

arXiv:2602. 13061v2 Announce Type: replace-cross Abstract: The ability of Flow Matching (FM) to model complex conditional distributions has established it as the state-of-the-art for prediction tasks (e.

By Constantinos Tsakonas, Serena Ivaldi, Jean-Baptiste Mouret

diffusion robotics efficiency benchmarks safety

arXiv AI

Jun 30

Flow Matching in Feature Space for Stochastic World Modeling

arXiv:2606. 29059v1 Announce Type: cross Abstract: World modeling requires forecasting uncertain futures while preserving information useful for downstream perception.

By Francois Porcher, Nicolas Carion, Karteek Alahari, Shizhe Chen

diffusion multimodal benchmarks

arXiv AI

Aug 12

Two-stage Odd Residual Flows for Mean-Preserving Probabilistic Time Series Forecasting

arXiv:2608. 11114v1 Announce Type: cross Abstract: Probabilistic forecasting plays an essential role in risk-sensitive decision-making, particularly in long-horizon settings.

By Kiran Madhusudhanan, Christian Kl\"otergens, Lars Schmidt-Thieme, Vijaya Krishna Yalavarthi

diffusion benchmarks

arXiv AI

Jul 15

Self-Consistent Flow: Unifying Velocity and Endpoint Prediction for Rectified Flow Models

arXiv:2607. 12171v1 Announce Type: cross Abstract: In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or the data endpoint, to perform denoising.

By Xu Han, Jiajing Hu, Li-Ping Liu

diffusion

Hugging Face Trending Papers

Jul 13

Self-Consistent Flow: Unifying Velocity and Endpoint Prediction for Rectified Flow Models

In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or the data endpoint, to perform denoising. Although prior work shows that these parameterizations lead to different empirical behaviors, the mechanisms underlying their respective advantages remain to be underexplored, and how to combine them effectively is still unclear.

diffusion

arXiv Machine Learning

1d ago

Is Flow Matching Just Trajectory Replay for Sequential Data?

arXiv:2602.08318v3 Announce Type: replace-cross Abstract: Flow matching (FM) is increasingly used in scientific domains for time series generation and forecasting, where data often arise from underly...

By Soon Hoe Lim, Shizheng Lin, Michael W. Mahoney, N. Benjamin Erichson

diffusion

Related stories