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).
More from Multimodal
- One Neon prompt turns a monstera plant into a walking, waving character — fofrAI · 2026-11-19
- Kezek splits mono two-person conversations into per-speaker tracks for full-duplex dialogue training data — manifestro · 2026-11-19
- LTX-2.3 long-form lessons: CFG=1 kills negative prompts, brightness drifts per clip — Chance-Thanks-1278 · 2026-11-19
- 6-minute Hubble documentary made with Claude and Jimeng CLI workflows — xiaohu · 2026-11-19
- Seedance 2.5 4K hands-on: AI video finally loses its plastic look — xiaohu · 2026-11-19
- Eerie AI-generated portraits: neon grimace faces and glowing-eyed shadows — azed_ai · 2026-11-19