EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models
EvoWorld gives generative video models a reasoning layer for events that happen off-screen, improving subject memory, causal reactions, and revisit consistency.
ls ./papers | grep "#video world models"
Trending AI research papers from Hugging Face, summarized in plain language: what each paper does, why it matters and where to read more.
3 papers · #video world models
EvoWorld gives generative video models a reasoning layer for events that happen off-screen, improving subject memory, causal reactions, and revisit consistency.
A survey explains why video generators need agent harnesses for planning, memory, interaction, evaluation, and possible recursive improvement—and why the strongest autonomy claims remain unproven.
PDRVLA introduces compact physical tokens to vision-language-action models, improving robot manipulation by anticipating scene dynamics without costly video generation.