arXiv Machine Learning October 22, 2026 By Yunpeng Mei, Xiaowen Zhu, Chenyu Wang, Chenbo Xin, Hongjie Cao, Jiamin Wang, Jie Chen, Gang Wang

Velocity Ambiguity Profiles: Time-Resolved Bayes-Risk Diagnostics for Flow Matching

Read the original on arXiv Machine Learning →

The paper introduces the Velocity Ambiguity Profile (VAP), a time‑local Bayes‑risk floor for velocity prediction in flow matching, and decomposes the loss into an irreducible ambiguity term and a reducible excess term. It provides statistical benchmarks for intrinsic local‑regression and Gaussian‑mixture scenarios, and validates the diagnostic with controlled experiments and CIFAR‑100 DINOv2 feature flow, showing that guided time sampling can reduce velocity loss and Fréchet distance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 7

Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average

arXiv:2607. 03809v1 Announce Type: new Abstract: Normalising flows provide a powerful variational family for approximate inference, yet individual architectures often fail to generalise across heterogeneous posterior geometries.

By Benjamin Wiriyapong, Oktay Karakus, Can Eyupoglu, Kirill Sidorov

multimodal benchmarks

arXiv Machine Learning

Aug 27

Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching

arXiv:2608. 25138v1 Announce Type: new Abstract: Stochastic masking, cropping, or modality removal makes deterministic reconstruction an incomplete target: one observation can admit many clean completions.

By Jiarui Cao

diffusion multimodal benchmarks

arXiv Machine Learning

Jun 5

Coreset-Induced Conditional Velocity Flow Matching

arXiv:2605. 12951v2 Announce Type: replace-cross Abstract: We propose Coreset-Induced Conditional Velocity Flow Matching (CCVFM), a generative model that augments hierarchical rectified flow with a data-informed source distribution.

By Xiao Wang, Zihua She, Jianxi Su

diffusion multimodal

arXiv Machine Learning

Aug 3

Conditioning Tree-Based Diffusions and Flows for Probabilistic Tabular Regression

arXiv:2607. 28864v1 Announce Type: cross Abstract: Tree-based diffusion models fit flexible conditional predictive distributions for tabular regression without a neural density estimator, but they inherit their design defaults---noising path, parameterization, training distribution, features, sampler---from the neural setting.

By Silas Koemen

diffusion benchmarks

arXiv Machine Learning

Jun 5

Gradient-Flow Optimization as Dynamic Random-Effects Inference: Testing and Early Stopping with Applications to Deep Learning

arXiv:2605. 27991v2 Announce Type: replace-cross Abstract: Gradient-flow optimization is usually viewed as an algorithmic procedure for minimizing empirical loss, with training duration selected by validation or heuristic early-stopping rules.

By Minhao Yao, Ruoyu Wang, Xihong Lin, Lin Liu, Zhonghua Liu

arXiv Machine Learning

Aug 13

Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flows

arXiv:2608. 11544v1 Announce Type: cross Abstract: We propose CVaR-penalized Generative Particle Algorithm (CVaR-GPA), a robust, tail-agnostic algorithm for fine-tuning generative models to learn heavy-tailed distributions and capture extreme events, requiring no prior knowledge or estimation of the target's tail characteristics.

By Thejani Gamage, Hyemin Gu, Zhizhen Zhang, Ziyu Chen, Markos Katsoulakis, Luc Rey-Bellet

fine-tuning

One email a morning, machine-written

Related stories

Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average

Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching

Coreset-Induced Conditional Velocity Flow Matching

Conditioning Tree-Based Diffusions and Flows for Probabilistic Tabular Regression

Gradient-Flow Optimization as Dynamic Random-Effects Inference: Testing and Early Stopping with Applications to Deep Learning

Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flows