Curating the frontier of Artificial Intelligence

Personalized physical therapy: Stroke rehabilitation powered by AI

中风是全球死亡和残疾的主要原因之一, 每年影响 1500 万人，并导致 500 万人受到长期影响...

Stroke is one of the leading causes of death and disability worldwide, affecting 15 million people each year and leaving 5 million with long-term impa...

With a feel for physics, AI models simulate a wider range of real

人工智能模型可以胜任许多行业,，包括编写,、生成图像, 和创建 3D 模型。但当……时它们’t没有那么有帮助。

Artificial intelligence models are jacks of many trades, including writing, generating images, and creating 3D models. But they aren’t as helpful when...

GENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis

基础模型正在改变业务工作流程并提高生产力,，但它们在电力等工程领域中仍然基本上缺席......

Foundation models are transforming business workflows and boosting productivity, yet they remain largely absent from engineering domains such as power...

Interaction Creates Dynamical AI Behavior Absent in Isolation

当人工智能代理在日常生活中交互时会发生什么,当一个 AI 开始在? 左右指挥另一个 AI 时，我们找到了一个违反直觉的答案，该答案打开...

What will happen when AI agents interact in daily life, e.g. when one AI starts bossing another around? We find a counterintuitive answer that opens n...

With a feel for physics, AI models simulate a wider range of real

人工智能模型可以胜任许多行业,，包括编写,、生成图像, 和创建 3D 模型。但当……时它们’t没有那么有帮助。

Artificial intelligence models are jacks of many trades, including writing, generating images, and creating 3D models. But they aren’t as helpful when...

TS-RAG: Retrieval Augmented Generation for Time Series Forecasting

虽然深度学习模型,尤其是基于变压器的架构,在时间序列预测,应用程序中表现出了令人印象深刻的性能...

While deep learning models, particularly transformer-based architectures, have shown impressive performance in time series forecasting, the applicatio...

DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models

具有可验证奖励的强化学习(RLVR) 使用自动可验证输出提高大型语言模型的推理能力...

Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models using automatically verifiable outc...

Improving the Realism of Synthetic Clinical Benchmarks Under Utility Constraints

企业人工智能代理的综合临床基准可以通过现有的实用程序检查，但在结构上仍然不切实际,，尤其是在私人领域……

Synthetic clinical benchmarks for enterprise AI agents can pass existing utility checks and still remain structurally unrealistic, especially in priva...

The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images

"thinking-with-images"范式为多模式法学硕士配备了主动视觉操作，例如裁剪和缩放。然而,模型使用这些操作...

The "thinking-with-images" paradigm equips multimodal LLMs with active visual operations such as crop-and-zoom. However, models using these operations...

QuanTiMedAI: Quantum-Enhanced Time-Series Model guided by Agentic AI for Cardiac Arrest Mortality Prediction

心脏骤停仍然是重症监护室遇到的最致命的情况之一。尽管电子医疗保健的可用性不断增加...

Cardiac arrest remains one of the most lethal conditions encountered in intensive care units. Despite the growing availability of electronic health re...