Curating the frontier of Artificial Intelligence

What Makes a Good Terminal-Agent Benchmark Task: A Guideline for Adversarial, Difficult, and Legible Evaluation Design

终端代理基准测试已成为衡量大型语言模型的编码和系统管理能力的主要信号。作为...

Terminal-agent benchmarks have become a primary signal for measuring the coding and system-administration capabilities of large language models. As th...

Mapping the Methodological Space of Classroom Interaction Research: Scale, Duration, and Modality in an Age of AI

课堂互动的研究长期以来分为大规模观察和深入的民族志工作。我们提出了一个框架映射...

Research on classroom interaction has long been divided between large-scale observation and in-depth ethnographic work. We propose a framework mapping...

Splitting Argumentation Frameworks with Collective Attacks and Supports

这项工作提出了论证形式主义的新颖分裂技术，其中结合了可废止元素之间的支持。我们的研究基础...

This work proposes novel splitting techniques for argumentation formalisms that incorporate supports between defeasible elements. We base our studies ...

Normativity and Productivism: Ableist Intelligence? A Degrowth Analysis of AI Sign Language Translation Tools for Deaf People

任何地理或口音变化的手语, 可以理解的是，在口头命令的普遍流行下，手语, 面临着持续的审查...

Sign languages, of any geographical or accentual variation, understandably face continuous scrutiny under the ever present popularity of verbal dictat...

Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists

现有的研究基础设施基本上是以文档为中心的,提供论文之间的引用链接，但缺乏对我的明确表示......

Existing research infrastructure is fundamentally document-centric, providing citation links between papers but lacking explicit representations of me...

LLM as Clinical Graph Structure Refiner: Enhancing Representation Learning in EEG Seizure Diagnosis

脑电图(EEG) 信号对于自动癫痫检测, 至关重要，但其固有的噪声使稳健的表示学习面临挑战......

Electroencephalogram (EEG) signals are vital for automated seizure detection, but their inherent noise makes robust representation learning challengin...

Synthetic Computers at Scale for Long-Horizon Productivity Simulation

现实的长期生产力工作很大程度上取决于用户特定的计算机环境,，其中存储了大部分工作上下文并......

Realistic long-horizon productivity work is strongly conditioned on user-specific computer environments, where much of the work context is stored and ...

Improving understanding with language

当她还是个孩子, 麻省理工学院大四学生奥利维亚·霍尼卡特 (Olivia Honeycutt) 时，她会在伯明翰郊外的阿拉巴马州乡村的祖父母 农场度过夏天。实用且...

When she was a child, MIT senior Olivia Honeycutt would spend summers on her grandparents’ farm in rural Alabama outside Birmingham. The practical and...

Beacon Biosignals is mapping the brain during sleep

人脑仍然是医学上最迷人和最令人困惑的谜团之一。科学家们仍在努力将神经活动与......

The human brain remains one of the most fascinating and perplexing mysteries in medicine. Scientists still struggle to match neurological activity wit...

Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations

运营和维护(O&M)大型在线引擎系统(eg,搜索,推荐和广告)需要大量人力来重新...

Operating and maintaining (O&M) large-scale online engine systems (eg, search, recommendation and advertising) demands substantial human effort for re...