PhysOPSD: Code as Privilege for Physically Plausible Video Generation
PhysOPSD uses executable simulations as privileged context for video-model training, improving physical plausibility with 3,000 samples while preserving general video quality.
ls ./papers | grep "#Generative video models"
Trending AI research papers from Hugging Face, summarized in plain language: what each paper does, why it matters and where to read more.
2 papers · #Generative video models
PhysOPSD uses executable simulations as privileged context for video-model training, improving physical plausibility with 3,000 samples while preserving general video quality.
EvoWorld gives generative video models a reasoning layer for events that happen off-screen, improving subject memory, causal reactions, and revisit consistency.