EvoWorld enables causal evolution in generative video models
EvoWorld uses a vision-language model as world brain and autoregressive renderer for out-of-sight causal evolution
9 stories, newest first · one card per story
EvoWorld uses a vision-language model as world brain and autoregressive renderer for out-of-sight causal evolution

Three months after Musk promised a full film, Grok calls the clip Episode 1, made with Wonder Studios and Dev Walker.
The authors propose a BoLe split: machines screen service content and trusted people judge work-type content.
ALIVE inserts objects into videos so they interact coherently, using only an edited first frame.
PhysVista tests whether VLMs can perceive, reason about, and judge physical plausibility in real and generated video.

TBC plans a neuron-inspired video adapter, but the commercial model and performance claims remain unverified.

ByteDance launched Dramagic, an AI platform that produces short dramas from script through video preview.

Runway previews research on real-time AI video generation using its GWM-1 world model to cut wait times and GPU costs.

AI studio Fountain 0 released the 2.5-hour fully AI-generated film 'Odysseus: The Fall,' which reviewers panned for severe visual and audio consistency failures.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views