Publication Catalog

所有文章

All published intelligence, sovereign stack research, ecosystem news, and AI foundation model reviews.

5282
Stories
Стартапы1 мин

自主投资的受控自我进化:具有不变核心的多代理 LLM 系统

arXiv:2610.30557v1 公告类型:新 摘要:作用于实时 Web 数据的 LLM 代理必须结合异构证据,记住他们所做的事情并从结果中进行改进,同时不削弱自己的保护措施。我们在自主投资中研究这个问题,其中每个......

arXiv — cs.AI
Исследования1 мин

串谋的模型生物:不受信监视器中的纠正性迁移

arXiv:2610.30582v1 通告类型:new 摘要:AI控制协议旨在通过监控模型行为,从可能未对齐的模型中获得有用工作。一种方法使用同一模型的第二个副本作为监视器。这避免了依赖模型可能利用的较弱审查者……

arXiv — cs.AI
Исследования1 мин

PLE: 物理工程的最后考试

arXiv:2610.30537v1 发布类型: 新 摘要: 前沿语言模型现在在流行知识基准测试中得分超过90%,并越来越多地作为执行多小时专业工作的代理被部署。然而,现有基准测试没有测试它们是否能够执行...

arXiv — cs.AI
Исследования1 мин

利用AI代理建模框架加速加拿大全境野火隐患测绘

arXiv:2610.30170v1 通告类型: 新 摘要: 加拿大日益增加的野火活动需要频繁的国家级隐患测绘以指导主动缓解措施,包括燃料管理、土地利用规划、基础设施保护和疏散路线规划。然而,基于过程的...

arXiv — cs.AI
Исследования1 мин

当稳定语义与优选语义一致时:基于路径的方法

arXiv:2610.30176v1 公告类型:新 摘要:我们研究抽象论证框架中优选语义与稳定语义一致的结构条件。我们的方法基于攻击图中适当选择的路径集合及其诱导的二元关系……

arXiv — cs.AI
Исследования1 мин

Why Bother Me Again? Benchmarking Personal Agent Memory for Interaction Preferences

arXiv:2610.30485v1 Announce Type: new Abstract: Personal intelligence systems are taking on increasingly complex everyday tasks, yet repeated questions, unnecessary confirmations, and unwanted outreach can turn capable assistance into interaction burden. Reducing this burden…

arXiv — cs.AI
Исследования1 мин

具有可微置信函数层的神经网络

arXiv:2610.30173v1 公告类型:新 摘要:Yager 1987 年的组合规则 $\boxplus$ 是基于认识论基础提出的:在高度冲突下,质量应该重新分配到无知,而不是重新归一化到类单纯形上。我们观察到反向传播需要……

arXiv — cs.AI
Исследования1 мин

6G通信系统中的安全代理AI与多模态智能

arXiv:2610.30436v1 发布类型: 新 摘要: 第六代(6G)通信系统预计将通过多模态智能、边缘计算和自主网络控制的紧密集成,支持沉浸式、意图驱动和对延迟敏感的服务。在...

arXiv — cs.AI
Исследования1 мин

问答:AI 如何开始模拟“混乱”的人类思维

生成式人工智能模型植根于20世纪中叶工程师的理念,他们认为一定程度的非理性对于能像人类一样思考的机器至关重要,麻省理工学院历史系助理教授本杰明·林德奎斯特主张……

MIT News — AI
База знаний1 мин

How Image Watermarking Works - Computerphile

Last time we looked at embedding watermarks in text output from well, usually AI, right? So, any generative process. I thought it might be more interesting to look at the image side of things because watermarks are also being embedded in images. And given that I work in computer…

YouTube — Computerphile AI
База знаний1 мин

How To Stand Out In A World Of AI Designs

Today, I'm joined by Alex Danilovich, co-founder and CEO of Magic Patterns, an AI design tool that takes you from an idea to a real interactive code-backed prototype in minutes. We'll look under the hood to see how Magic Patterns works, hear his origin story as a non-designer,…

YouTube — Y Combinator AI
База знаний1 мин

MCP Security Fundamentals Course

Thanks for checking out this MCP security course. I'm Dan Barahona, founder of AI Security University. And this video is part of our suite of free courses and weekly live events. Stick around till the end of the video and you'll have a chance to take a final quiz, earn your…

YouTube — freeCodeCamp AI
Исследования1 мин

What Is LLM Inference? How AI Models Generate Responses

Training a Frontier model can cost hundreds of millions of dollars and take months. But once that model is produced, it's just a huge set of numbers sitting idly in memory. A model doesn't know how to do anything on its own. So what's going on behind the scenes to bring that…

YouTube — IBM Technology AI
База знаний1 мин

The last real programmers are dying out...

the programmer. Four years ago, science classified 10 known variants of this animal, and the taxonomy held up pretty well until an asteroid hit in 2023 and nearly wiped them off the Earth. Since then, the habitat has changed. The nine out of 10 developers are now using AI to…

YouTube — Fireship AI
База знаний1 мин

梅西请求 ChatGPT 教他国际象棋开局

梅西请求 ChatGPT 教他一个符合他风格的国际象棋开局。它建议使用山羊角。 🐐🤘 亲自尝试 ChatGPT 的智能 UI:“根据您对我的了解,教我一些新知识。一步一步向我展示。”

YouTube — OpenAI Official