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Learned Cross-Task Relationships in Multi-Task Models

arXiv:2609.28776v1 Announce Type: new Abstract: We propose a framework that learns cross-task relationships in multi-task models by approximating the joint distribution of task labels through targeted pairwise relationships. This approach improves performance via transfer…

arXiv — cs.AI作者: Victor Zhang, Yiping Yuan, Florian Raudies, Bosun Adeoti, Brian Y. C. Leung, Sanjay Surendranath Girija, Naijing Zhang2026年9月25日 (9月25日)
提供 1 种语言版本

AI 摘要:要点

  • arXiv:2609.28776v1 Announce Type: new Abstract: We propose a framework that learns cross-task relationships in multi-task models by approximating the joint distribution of task labels through targeted pairwise relationships
  • This approach improves performance via transfer…
Research
KZ·AI 1DB4
Инсайт дня

Learned Cross-Task Relationships in Multi-Task Models

标签:#arXiv
Поделиться:

相关文章

返回列表