yxc0433
·
2026-06-10
·
5 min
AI
[2606.09809] 评估卡: AI 评估报告的解释层
[2606.09809] Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting
提交历史记录 访问论文: 当前浏览上下文: 参考文献 & 引文 BibTeX 格式的引文书签 arXivLabs 是一个框架,允许...
Submission history Access Paper: Current browse context: References & Citations BibTeX formatted citation Bookmark arXivLabs is a framework that allow...
01
Adam Conner-Simons | MIT Media Lab
·
2026-06-10
·
4 min
AI
依靠人工智能获取准确新闻的后果
The consequences of relying on AI for accurate news
过去几年,人工智能在一般信息收集方面的应用出现了大规模爆炸式增长,这已经不是什么秘密了。一个甚至...
It’s no secret that the last few years have seen a massive explosion in the use of artificial intelligence for general information-gathering. An even ...
02
yxc0433
·
2026-06-09
·
7 min
AI
[2606.07462] 作为真正的研究人员: 一套评估研究生命周期中的前沿法学硕士和代理工具的基准
[2606.07462] Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle
提交历史记录 访问论文: 当前浏览上下文: 参考文献 & 引文 BibTeX 格式的引文书签 arXivLabs 是一个框架,允许...
Submission history Access Paper: Current browse context: References & Citations BibTeX formatted citation Bookmark arXivLabs is a framework that allow...
03
yxc0433
·
2026-06-09
·
4 min
AI
[2606.07489] AI 代理如何重塑知识工作: 自主性, 效率, 和范围
[2606.07489] How AI Agents Reshape Knowledge Work: Autonomy, Efficiency, and Scope
提交历史记录 访问论文: 当前浏览上下文: 参考文献 & 引文 BibTeX 格式的引文书签 arXivLabs 是一个框架,允许...
Submission history Access Paper: Current browse context: References & Citations BibTeX formatted citation Bookmark arXivLabs is a framework that allow...
04
yxc0433
·
2026-06-08
·
6 min
AI
[2606.06356] 知识应该从哪里进入? 多模式迭代生成模型中知识注入的分层框架
[2606.06356] Where Should Knowledge Enter? A Layered Framework for Knowledge Infusion in Multimodal Iterative Generative Mo
提交历史记录 访问论文: 当前浏览上下文: 参考文献 & 引文 BibTeX 格式的引文书签 arXivLabs 是一个框架,允许...
Submission history Access Paper: Current browse context: References & Citations BibTeX formatted citation Bookmark arXivLabs is a framework that allow...
05
yxc0433
·
2026-06-08
·
4 min
AI
[2606.06360] 基于大语言模型决策的传染病传播模拟
[2606.06360] An Infectious Disease Spread Simulation Based on Large Language Model Decision Making
提交历史记录 访问论文: 当前浏览上下文: 参考文献 & 引文 BibTeX 格式的引文书签 arXivLabs 是一个框架,允许...
Submission history Access Paper: Current browse context: References & Citations BibTeX formatted citation Bookmark arXivLabs is a framework that allow...
06
yxc0433
·
2026-06-08
·
10 min
AI
[2606.06375] 重新思考基础设施检查作为图像差异分类: 交通标志案例研究
[2606.06375] Rethinking Infrastructure Inspection as Image Difference Classification: A Traffic Sign Case Study
提交历史记录 访问论文: 当前浏览上下文: 参考文献 & 引文 BibTeX 格式的引文书签 arXivLabs 是一个框架,允许...
Submission history Access Paper: Current browse context: References & Citations BibTeX formatted citation Bookmark arXivLabs is a framework that allow...
07
yxc0433
·
2026-06-08
·
3 min
AI
[2606.06388] Humans ALMANAC: 人类协作行动数据集
[2606.06388] Humans' ALMANAC: A Human Collaboration Dataset of Action
提交历史记录 访问论文: 当前浏览上下文: 参考文献 & 引文 BibTeX 格式的引文书签 arXivLabs 是一个框架,允许...
Submission history Access Paper: Current browse context: References & Citations BibTeX formatted citation Bookmark arXivLabs is a framework that allow...
08
yxc0433
·
2026-06-07
·
10 min
AI
[2606.06396] 自动驾驶风险评估: 整合技术故障, 道德困境, 和政策框架
[2606.06396] Risk Assessment of Autonomous Driving: Integrating Technical Failures, Ethical Dilemmas, and Policy Frameworks
提交历史记录 访问论文: 当前浏览上下文: 参考文献 & 引文 BibTeX 格式的引文书签 arXivLabs 是一个框架,允许...
Submission history Access Paper: Current browse context: References & Citations BibTeX formatted citation Bookmark arXivLabs is a framework that allow...
09
yxc0433
·
2026-06-07
·
5 min
AI
[2606.06416] 用于代理数据分析的无监督技能发现
[2606.06416] Unsupervised Skill Discovery for Agentic Data Analysis
提交历史记录 访问论文: 当前浏览上下文: 参考文献 & 引文 BibTeX 格式的引文书签 arXivLabs 是一个框架,允许...
Submission history Access Paper: Current browse context: References & Citations BibTeX formatted citation Bookmark arXivLabs is a framework that allow...
10