RISA:面向块扩散语言模型的可恢复稀疏注意力
arXiv 通过 DataCite 签发的 DOI(待注册)
来自:Xinrui Zhong [查看邮箱] [v1] 2026年11月17日 星期二 04:27:48 UTC(314 KB)
查看论文 PDF:RISA: Recoverable Sparse Attention for Block-Diffusion Language Models,作者 Xinrui Zhong、Fanjiang Ye、Yuke Wang
BibTeX 格式引用
文献与引用工具
Bibliographic Explorer(什么是 Explorer?)
Connected Papers(什么是 Connected Papers?)
scite Smart Citations(什么是 Smart Citations?)
与本文相关的代码、数据和媒体
CatalyzeX Code Finder for Papers(什么是 CatalyzeX?)
Hugging Face(什么是 Huggingface?)
Hugging Face Spaces(什么是 Spaces?)
推荐器与搜索工具
Influence Flower(什么是 Influence Flowers?)
CORE Recommender(什么是 CORE?)
arXivLabs:与社区合作者开展的实验性项目
arXivLabs 是一个框架,让合作者可以直接在我们的网站上开发和分享新的 arXiv 功能。
与 arXivLabs 合作的个人和组织都认同并接受了我们开放、社区、卓越和用户数据隐私的价值观。arXiv 坚守这些价值观,只与遵循这些价值观的合作伙伴合作。
有能为 arXiv 社区创造价值的项目想法?了解关于 arXivLabs 的更多信息。
译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。
查看英文原文(RISA: Recoverable Sparse Attention for Block-Diffusion Language Models)
arXiv-issued DOI via DataCite (pending registration)
From: Xinrui Zhong [view email]
[v1]
Tue, 17 Nov 2026 04:27:48 UTC (314 KB)
View a PDF of the paper titled RISA: Recoverable Sparse Attention for Block-Diffusion Language Models, by Xinrui Zhong and Fanjiang Ye and Yuke Wang
BibTeX formatted citation
Bibliographic and Citation Tools
Bibliographic Explorer(What is the Explorer?)
Connected Papers(What is Connected Papers?)
scite Smart Citations(What are Smart Citations?)
Code, Data and Media Associated with this Article
CatalyzeX Code Finder for Papers(What is CatalyzeX?)
Hugging Face(What is Huggingface?)
Hugging Face Spaces(What is Spaces?)
Recommenders and Search Tools
Influence Flower(What are Influence Flowers?)
CORE Recommender(What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
原文为英文,正文由自动抓取并保留原文。
原文发布于 arXiv cs.CL(RISA: Recoverable Sparse Attention for Block-Diffusion Language Models),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。