#THE

安全攻防 None

TrapDoor 供应链攻击通过 npm、PyPI 和 CratesIO 传播窃取凭证的恶意软件

A new coordinated cross-ecosystem software supply chain attack campaign has targeted npm, PyPI, and Crates。io to distrib

new campaign The

2026-05-25 info@thehackernews.com (The Hacker News)

开发者生态 None

Jira 是图灵完备的

Nicolas Seriot Computation > Jira is Turing-Complete Jira is Turing-Complete Building a Minsky Machine in Atlassian Auto

goto Jira and

2026-05-25 vinhnx

开发者生态 None

公司只是算法图

Companies Are Just a Graph of Algorithms AI is about to see your company as a series of components to be optimized May 6

the that you

2026-05-25 samuel246

开源推荐 None

GitHub 热门项目：AgiBot-World

GitHub项目：AgiBot-World 仓库地址：https://github。

https AgiBot World

2026-05-25 GitHub Trending

开源推荐 None

GitHub 热门项目：mistral-finetune

GitHub项目：mistral-finetune 仓库地址：https://github。

the mistral finetune

2026-05-25 GitHub Trending

开源推荐 None

GitHub 热门项目：xzbot

GitHub项目：xzbot 仓库地址：https://github。

the patch backdoor

2026-05-25 GitHub Trending

开源推荐 None

GitHub 热门项目: 遗忘

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

and the WireGuard

2026-05-25 GitHub Trending

开源推荐 None

GitHub 热门项目： Trailbase

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

trailbase the https

2026-05-25 GitHub Trending

开发者生态 None

永恒的沉睡

I’m calling it now, the adoption of AI agents into software development will be one of the most costly mistakes in the f

the you and

2026-05-25 razin

开发者生态 None

用 Pi 构建 Pi

Armin Ronacher 's Thoughts and Writings blog archive projects travel talks about Building Pi With Pi written on May 24,

the and but

2026-05-25 mplanchard

智能AI None

LLM 何时进行推理？通过熵相变的动态系统视图

arXiv:2605.22873v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning has become the default strategy for enh

and entropy reasoning

2026-05-25 Wei Xia, Haoqing Wang, Zhi-Hong Deng, Yehui Tang

智能AI None

MedExpMem：调整经验记忆以进行鉴别诊断

arXiv:2605.22872v1 Announce Type: new Abstract: Experienced physicians develop diagnostic expertise through clinical pra

and diagnostic the

2026-05-25 Qianhan Feng, Zhongzhen Huang, Yakun Zhu, Yannian Gu, Winnie Chiu Wing Chu, Xiaofan Zhang, Qi Dou

智能AI None

通过自模式连接引导的流形表示遗忘来近似机器遗忘

22871v1 Announce Type: new Abstract: Machine unlearning is a fundamental mechanism that enforces the right to be forgott

the unlearning textbf

2026-05-25 Weiqi Wang, Zhiyi Tian, Chenhan Zhang, Luoyu Chen, Shui Yu

智能AI None

读出捷径：位置数字复制在小语言模型中主导算术 CoT 读出

22870v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting is necessary for arithmetic in small language mode

the answer CoT

2026-05-25 Ming Liu

智能AI None

FuRA：利用光谱预处理进行全秩参数高效微调

arXiv:2605.22869v1 Announce Type: new Abstract: Both full fine-tuning (Full FT) and parameter-efficient fine-tuning meth

the and full

2026-05-25 Yequan Zhao, Ruijie Zhang, Liyan Tan, Niall Moran, Tong Qin, Zheng Zhang

智能AI None

从语言模型轨迹中读取校准的不确定性

arXiv:2605.22864v1 Announce Type: new Abstract: The maximum softmax probability (MSP) represents a default approach when

the probe and

2026-05-25 Aliai Eusebi, Alexander Herzog, Xiaoyu Liang, Marie Vasek, Enrico Mariconti, Lorenzo Cavallaro

智能AI None

潜在缓存流：无文本的模型到模型通信

arXiv:2605.22863v1 Announce Type: new Abstract: LLM agents today communicate via text, which incurs considerable latency

the and model

2026-05-25 Maximillian Rossi, Prajwal Raghunath, Eugene Wu

智能AI None

EVE-Agent：证据可验证的自我进化代理

22905v1 Announce Type: new Abstract: Self-evolving agents should not train on examples they cannot justify。

that evidence the

2026-05-25 Yamato Arai, Yuma Ichikawa

智能AI None

中介模糊逻辑：从 Type-1 基础到 Type-2、Type-3 和量子扩展

22900v1 Announce Type: new Abstract: Mediative Fuzzy Logic was conceived as a practical scheme for reconciling hesitant

and type the

2026-05-25 Oscar Montiel Ross

智能AI None

每个成功目标的能量：代理人工智能系统的目标级能量核算

22883v1 Announce Type: new Abstract: Current AI energy benchmarks measure consumption at the granularity of a single mod

energy the and

2026-05-25 Deepak Panigrahy, Aakash Tyagi