#knowledge

开发者生态 None

Knowledge Should Not Be Gated

For most of the last few years, giving an AI system knowledge meant building infrastructure。You wanted your agent to kno

the you knowledge

2026-07-05 nezhar

智能AI None

用于心理健康药物信息检索的知识增强代理人工智能

arXiv:2606.26205v1 Announce Type: new Abstract: Patients increasingly seek medication information online, yet safety kno

and for patient

2026-06-26 Huizi Yu, Jian Liu, Wenkong Wang, Lingyao Li, Jiayan Zhou, Zhaoqian Xue, Xiang Li, Xinxin Lin, Zhiying Liang, Zhuoru Wu, Siyuan Ma, Xin Ma, Lizhou Fan

智能AI None

资源限制下的路径依赖程序归纳解释了人类序列学习

20623v1 Announce Type: new Abstract: How do people build abstract, reusable knowledge from sequential experience under b

and program knowledge

2026-06-23 Hanqi Zhou, David G. Nagy, Peter Dayan, Charley M. Wu

智能AI None

配对时正确，分割时错误：解耦和编辑 MLLM 中的模态特定神经元

arXiv:2606.17057v1 Announce Type: new Abstract: Although Knowledge Editing provides an efficient mechanism for updating

knowledge the that

2026-06-17 Tingchao Fu, Wenkai Wang, Fanxiao Li, Huadong Zhang, Jinhong Zhang, Dayang Li, Yunyun Dong, Renyang Liu, Wei Zhou

开源推荐 None

GitHub 热门项目：理解任何东西

GitHub项目：Understand-Anything 仓库地址：https://github。com/Egonex-AI/Understand-Anything Stars：57707 | 作者：Egonex-AI 项目描述：Graph

Understand Anything and

2026-06-12 GitHub Trending

开源推荐 None

GitHub 热门项目：理解任何东西

GitHub项目：Understand-Anything 仓库地址：https://github。com/Lum1104/Understand-Anything Stars：39546 | 作者：Lum1104 项目描述：Graphs th

and Understand Anything

2026-05-27 GitHub Trending

智能AI None

约束获取需要更好的基准

arXiv:2605.26279v1 Announce Type: new Abstract: Constraint Acquisition (CA) and related research on the validation and e

and the models

2026-05-27 Rafa{\l} Stachowiak, Tomasz P. Pawlak

智能AI None

教大模型终身学习！中科大连发两篇顶会，突破「知识注入」双重困境

新智元报道 【新智元导读】 中科大团队首先推出动态多模态知识注入基准MMEVOKE，解构遗忘机制，并在此基础上提出全新双阶段框架KORE。通过「知识树」自动增强与「零空间」协方差约束微调，为大模型终身学习开辟了全新路径。当前主流大型多模态模

MMEVOKE https KORE

2026-05-21 新智元

开源推荐 None

GitHub 热门项目：GitNexus

GitHub项目：GitNexus 仓库地址：https://github。

GitNexus com knowledge

2026-05-19 GitHub Trending

智能AI None

NOVA：通过人工智能发现知识的基本限制

15219v1 Announce Type: new Abstract: Can AI systems discover genuinely new knowledge through iterative self improvement,

the knowledge and

2026-05-18 Salman Avestimehr, Ken Duffy, Muriel M\'edard