Image created with gemini-3.1-flash-image-preview with claude-sonnet-4-5. Image prompt: Using the provided reference image, preserve the left-anchored close-crop profile composition, deep blue-purple cinematic lighting, emotional weight, and misty rightward haze, but replace the central figure with a person in three-quarter profile holding a cracked glass snow globe containing a miniature city, glitter particles escaping and catching light on their fingers and face, maintaining the melancholy post-party stillness and HBO prestige drama aesthetic, with ‘world models’ in thin lowercase white Helvetica Neue Light on the right two-thirds.
We’re excited to be rolling out two model updates today! Marble 1.1: Improves lighting and contrast, with a major reduction in visual artifacts. Marble 1.1-Plus: Our new model built for scale. Create larger, more complex environments than ever before.
https://x.com/theworldlabs/status/2041554646561677701
Making improvements one step at a time for Marble. In the case of generating bigger worlds, it’s quite literal 😉 🤩🌐
https://x.com/drfeifei/status/2041558772888563882
GEN-1 is like an internet scale world model. Cosmos trained on a few hundred K hrs GEN-1 trained on ½ Million GEN-1 appears to understand physics, has spatial and temporal intelligence, knows cause & effect And it transfers perfectly to real hardware
https://x.com/E0M/status/2041538897608659248
But we don’t call it a World Model nor a VLA. Doesn’t really matter what we call it. It just needs to hit our goals of having useful embodied intelligence.
https://x.com/E0M/status/2041539828555321784
Leave a Reply