What Lilian Weng thinks about world models

@lilian-weng · 16 positions · On ppll ↗

Machine-learning researcher; has written the Lil'Log survey posts on how a model technique works since 2017, and worked at OpenAI from 2018 to 2024.

Lilian Weng did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

Filter world models · Newest first

Topic

All 16 world models 1 LLMs 10 cybersecurity 3 AI alignment 2 design 2 neural networks 2 reinforcement learning 2 AI agents 1 AI and human skill 1

4 more topics

AI and science 1 computer vision 1 recursive self-improvement 1 scaling laws 1

Sort

Newest Oldest

Only Lilian Weng on world models. See everyone on world models

1 dated position, 2024, in their own words. Our reading of what Lilian Weng has said — not written or endorsed by them.

1 position so far — this page is not yet offered to search engines.

12 Apr 2024

Our readingVideo generation requires more world knowledge than image generation because of the need for temporal consistency across frames.

Their wordsIt has extra requirements on temporal consistency across frames in time, which naturally demands more world knowledge to be encoded into the model.

↗Diffusion Models for Video Generationlilianweng.github.io 1st of 2 in this piece