Automating Chip I/O Design with AI

Researchers have developed a new AI-powered system that significantly accelerates the design of analog and mixed-signal integrated circuit input/output rings.

Researchers have developed a new AI-powered system that significantly accelerates the design of analog and mixed-signal integrated circuit input/output rings.

Researchers are leveraging the power of graph neural networks to better understand human actions by modeling the connections between visual cues and skeletal data.

New research reveals how deepfake detection models identify manipulated media by dissecting their internal feature representations.

New research exposes the hidden human effort powering artificial intelligence systems, revealing the precarious conditions faced by those performing this essential ‘ghost work’.

New research reveals that prioritizing computational resources on compressing information, rather than prediction, is a more effective pathway to building powerful agentic systems.

A new robotic intubation system combines advanced sensing and machine learning to improve the safety and accuracy of fiberoptic endotracheal intubation.

Researchers have developed a new system that automatically transforms raw data into compelling, publication-ready visualizations and accompanying reports.
![MoonBot, a modular and reconfigurable robotic system, demonstrates a capacity for scalable lunar base construction through adaptable configurations - ranging from a minimal unit composed of a limb and wheel ([latex]1\times\times Limb + 1\times\times Wheel[/latex]) to a more capable “Dragon” configuration formed by serially connected minimal units - enabling tasks such as terrain preparation, heavy equipment transport exceeding 30 kg, and the precise deployment of inflatable structures with integrated stabilization.](https://arxiv.org/html/2512.21853v1/x2.png)
Researchers have developed and field-tested MoonBot, a reconfigurable robotic system designed to autonomously construct habitats and infrastructure on the lunar surface.

New research compares the performance of attention-based neural networks and large language model prompting for automatically identifying relevant legal statutes from case descriptions.

A new framework empowers embodied agents to break down complex instructions into manageable steps, paving the way for more capable and adaptable robotic assistants.