Curating the frontier of Artificial Intelligence

Demystifying Data Organization for Enhanced LLM Training

大型语言模型 (LLMs) 已经彻底改变了各个领域,，但它们的训练效率在很大程度上依赖于有效的数据管理。虽然达...

Large Language Models (LLMs) have revolutionized various fields, yet their training efficiency is heavily reliant on effective data curation. While da...

Locally Coherent, Globally Incoherent: Bounding Compositional Incoherence in Multi-Component LLM Agents

多组件 LLM 代理从组件中组装概率声明，每个组件仅看到联合问题的一部分; 该组合可能违反基本...

Multi-component LLM agents assemble probabilistic claims from components that each see only part of a joint problem; the composition can violate basic...

Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection

视觉语言模型 (VLMs) 的最新进展在许多任务中取得了令人印象深刻的性能,，但之前的研究报告表现不令人满意...

Recent advances in Vision-Language Models (VLMs) have achieved impressive performance across many tasks, yet prior studies report unsatisfactory perfo...

SchGen: PCB Schematic Generation with Semantic-Grounded Code Representations

印刷电路板 (PCB) 原理图设计定义了几乎所有电子硬件,，但它仍然需要大量手动和专业知识。虽然生成A...

Printed circuit board (PCB) schematic design defines nearly all electronic hardware, but it remains manual and expertise-intensive. While generative A...

Physics Is All You Need? A Case Study in Physicist-Supervised AI Development of Scientific Software

AI 代理是工具, 合著者, 还是研究人员? 我们提出了量化案例研究($N=1$): 监督 AI 编码代理的物理学家(Claude Code, ...

Are AI agents tools, co-authors, or researchers? We present a quantified case study ($N=1$): a physicist supervising an AI coding agent (Claude Code, ...

CubePart: An Open-Vocabulary Part-Controllable 3D Generator

游戏和模拟中使用的交互式 3D 资源通常被分解为特定的语义部分，以支持动画, 物理, 和脚本化 b...

Interactive 3D assets used in games and simulation are typically decomposed into specific semantic parts to support animation, physics, and scripted b...

SwarmHarness: Skill-Based Task Routing via Decentralized Incentive-Aligned AI Agent Networks

个人工作站上的大量计算 (GPU 周期, 闲置推理服务器, 和作业之间的边缘设备) 未使用，因为没有激励...

Vast quantities of compute (GPU cycles on personal workstations, idle inference servers, and edge devices between jobs) go unused because no incentive...

CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models

脑电图(EEG) 是监测脑电活动的关键, 非侵入性方法。脑电图的跨度可以从几秒钟到......

Electroencephalography (EEG) is a critical, non-invasive method to monitor electrical brain activity. EEGs can span anywhere from a couple seconds to ...

Calibrating Conservatism for Scalable Oversight

能够自主规划和扩展环境交互的代理人工智能系统提出了一个基本的控制问题:人类如何维持...

Agentic AI systems capable of autonomous planning and extended environmental interaction pose a fundamental control problem: how can humans maintain m...

Media Advisory: MIT to establish regional quantum hub

QSL 将位于麻省理工学院校园 39 号楼，将作为一个拥有现代化实验基础设施的多学科量子中心。乙...

The QSL will be located at Building 39 on the MIT campus and will serve as a multi-disciplinary quantum hub with modern experimental infrastructure. B...