Research finds physics understanding in video diffusion models even when outputs are wrong

katjahofmann · x · 2026-11-19

Former Microsoft Research researcher Katja Hofmann highlights research led by her former interns Parsa Esmati and Somjit: video diffusion models encode an understanding of physics even when their generated outputs get the physics wrong. Co-advised with Derek, Samira Kahou and Majid Mirmehdi.

She will discuss the work in a talk at the AE Global Summit 2026 on Open Problems for AI, held 25-27 November 2026 at Friends House, London (tickets £45-£1000).

Original post →

More from Multimodal

Multimodal channel →