阿斯塔纳时间
AI QAZAQSTANKZ · AI测试版

哈萨克斯坦人工智能与高科技领域的智能门户

Research1 分钟阅读

内容来自原始来源：

arXiv — cs.AI

在 arXiv — cs.AI 阅读全文

本内容来自公开来源。若发布内容影响您的权利 → 申请删除信息

标题为英语MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching

Flow matching models excel at generative modeling, and many downstream applications require their samples to satisfy prescribed constraints, such as observed measurements and physical laws. However, existing constrained samplers often face a trade-off: \textit{enforcing…

arXiv — cs.AI作者: Yesom Park, Kelvin Kan, Qifan Chen, Thomas Flynn, Hayden Schaeffer. Xihaier Luo2026年10月5日 (10月5日)
提供 1 种语言版本

AI 摘要：要点

  • Flow matching models excel at generative modeling, and many downstream applications require their samples to satisfy prescribed constraints, such as observed measurements and physical laws
  • However, existing constrained samplers often face a trade-off: \textit{enforcing…
Research
KZ·AI 9919
Инсайт дня

MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching

标签：#arXiv
Поделиться:

相关文章

返回列表