Curating the frontier of Artificial Intelligence

Teaching AI models to say “I’m not sure”

A new training method improves the reliability of AI confidence estimates without sacrificing performance, addressing a root cause of hallucination in...

A new training method improves the reliability of AI confidence estimates without sacrificing performance, addressing a root cause of hallucination in...

MIT scientists build the world’s largest collection of Olympiad-level math problems, and open it to everyone

来自47个国家的30,000 +竞赛数学问题的新数据集为AI研究人员提供了更难的测试— ，为全球学生提供了更好的培训...

New dataset of 30,000-plus competition math problems from 47 countries gives AI researchers a harder test — and students worldwide a better training g...