Uploaded September 2023 | Updated September 2026, 1 week ago
As an accredited member of the Middle States Commission on Higher
Education, NYU conducts a self-study of the University once every
eight years. In honor of this year's study, we asked our students some
pretty specific questions about their school—and were impressed by
their answers! Read the 2023-2024 report:
https://www.nyu.edu/academics/accreditation-authorization-assessment/accreditation/2023-2024-self-study.html
As an accredited member of the Middle States Commission on Higher
Education, NYU conducts a self-study of the University once every
eight years. In honor of this year's study, we asked our students some
pretty specific questions about their school—and were impressed by
their answers! Read the 2023-2024 report:
https://www.nyu.edu/academics/accreditation-authorization-assessment/accreditation/2023-2024-self-study.html


![How Naturalistic Learning Algorithm PooDLe Works
Most AI systems trained on carefully curated datasets struggle when faced with the messy reality of naturalistic video. PooDLe [https://arxiv.org/abs/2408.11208], a newly published work, addresses this problem.
“We were interested in building embodied learning algorithms that could learn directly from video streams. Says Mengye Ren, author of the paper and assistant professor of computer science and data science at NYU.
The algorithms name comes from a combination of a pooled loss function and a dense loss function used in PooDLes architecture.
Visit nyu.edu/news for updates on this story and more. How Naturalistic Learning Algorithm PooDLe Works](https://i.ytimg.com/vi/uUotGDIibu8/mqdefault.jpg)







