Research paper

New research shows the most advanced AI models from China were trained on banned Nvidia chips.

作者称在三个问答基准上超过同等规模的端到端模型。

A research team from the Hefei Institutes of Physical Science, Chinese Academy of Sciences, and Hefei Cancer Hospital, together with domestic and international

Nature, Published online: 13 November 2026; doi:10.1038/d41586-026-03679-8 Being able to target and debug systems could improve artificial-intelligence safety a

Shoppers using AI chatbots to research products or find places to buy items could be directed to imposters and other risky websites, a new study found. The stud

Cybersecurity researchers have found that lookalike domains masquerading as artificial intelligence (AI) tools are being used to serve ClickFix-style lures, bro

MCP's request direction goes more than one way. Beyond clients calling tools, the protocol also lets servers make reverse requests to clients: sampling/createMe

Microsoft's FORGE lab used an AI-driven scanning system to discover 59 security vulnerabilities in the Linux kernel, some of which had gone undetected for more

Ads ranking models are growing toward LLM scale faster than the hardware to run them can keep up. An extra unit of compute has more impact on some ad requests,

Predicting how DNA sequences and their variations impact specific human cell types and disease.

Researchers in Germany gradually reversed human cells’ ages by decades. By doing so, they could track the de-aging process in a way previous rejuvenation experi

An AI model can be given a hidden backdoor by editing fewer than 10 of its rarely used neurons, without retraining the model, Microsoft researchers have shown.

Microsoft researchers confirmed that attackers can plant a hidden backdoor by modifying fewer than 10 rarely activated neurons in an AI model, without retrainin