Force Prompting: video generation models learn physics-based control signals
creatoroff · x · 2026-10-07
- Paper from Brown University and Google DeepMind: "Force Prompting: Video Generation Models Can Learn and Generalise Physics Based Control Signals" (Nate Gillman, Charles Herrmann, Chen Sun, et al.).
- The method teaches video generation models to obey and generalize physics-based control signals (e.g., forces), enabling physics-level control over generated video.
- An interactive Gemini Notebook accompanies the work.
More from Multimodal
- Voice Agents Live or Die on 'Sounding Right': Turbo Shifts Tone With User Emotion — SucceededMind · 2026-10-07
- Magnific Original Series The Chronicles of Bone drops Chapter Six, made entirely with AI tools — Kavanthekid · 2026-10-07
- Hedra Lands in ChatGPT: Attach One Product Photo, Get a Full Commercial Ad — henloitsjoyce · 2026-10-07
- Marc Andreessen boosts AI film contest SLOPTOBERFEST grand prize to $25,000 — zealcaiden · 2026-10-07
- Image generation pricing leak: $0.05 per 2K image, $0.076 per 4K — op7418 · 2026-10-07
- Live human votes plugged into Flow-GRPO to stop image models gaming reward models — lmoroney · 2026-10-07