arXiv Machine Learning August 13, 2026 By Thejani Gamage, Hyemin Gu, Zhizhen Zhang, Ziyu Chen, Markos Katsoulakis, Luc Rey-Bellet

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

Read the original on arXiv Machine Learning →

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.

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.

fine-tuning

arXiv AI

Jun 4

Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models

arXiv:2605. 18931v2 Announce Type: replace-cross Abstract: Heavy-tailed distributions are prevalent in performance evaluation, network traffic, and risk modeling.

By Abdelhakim Ziani, Andras Horvath, Paolo Ballarini

diffusion

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 Statistics ML

Aug 25

Generative Neural Networks for Sinkhorn Distributionally Robust Hypothesis Testing

arXiv:2608.22746v1 Announce Type: new Abstract: This paper studies the Sinkhorn distributionally robust hypothesis testing (SDRHT) problem, seeking a robust detector against least-favorable distribut...

By Fenglin Zhang, Teyan Liu, Jie Wang

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

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

3d ago

FluxLite: Inference-Time Proposal Control for Discrete Diffusion Models

arXiv:2609.35947v1 Announce Type: new Abstract: Many inference-time tasks for pretrained discrete diffusion models and diffusion language models reduce to drawing samples from a tilted version of the...

By Yinuo Ren, Haoxuan Chen, Grant M. Rotskoff, Jiequn Han, Lexing Ying

llms diffusion benchmarks

One email a morning, machine-written

Related stories

Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models

Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average

Generative Neural Networks for Sinkhorn Distributionally Robust Hypothesis Testing

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

Coreset-Induced Conditional Velocity Flow Matching

FluxLite: Inference-Time Proposal Control for Discrete Diffusion Models