AI Briefing#world-model
The latest AI and developer news about #world-model, with the original source and a short summary.
The latest AI and developer news about #world-model, with the original source and a short summary.
Sub-JEPA boosts LeWM performance by splitting the high-dimensional Gaussian constraint and applying it separately.
NVIDIA has unveiled SANA-WM, which generates 1-minute 720p video with 6-DoF camera trajectories.
NVIDIA has released a 2.6B open-source world model for 1-minute 720p video.
Runway is challenging Google by expanding from video generation into world models.
LeCun believes world models, not LLMs, are the key to real-world intelligence.
World models have emerged as the key to real-world AI, but the data barrier makes their spread uncertain, the analysis says.
A survey of 400+ papers organizing agentic world models into a three-tier taxonomy and four domains has been published.
Odyssey has unveiled Odyssey-2 Max, a large world model for real-time interaction.
HY-World 2.0 creates editable 3D worlds from text, images, and video.
Tencent has open-sourced HY-World 2.0, an editable 3D world model.
Overworld has released Waypoint-1.5, a real-time generative world model that can run on consumer-grade GPUs.
ActionParty solves the 'action binding' problem, where video generation models fail to accurately assign different actions to multiple subjects.
Overworld has released Waypoint-1, a video diffusion model that supports real-time control via text and keyboard/mouse, along with the inference library WorldEngine.