Ant Group Open-Sources Embodied Video Model
量子位 · wechat · 2026-07-09
Ant Lingbo has open-sourced LingBot-Video, a large-scale MoE video foundation model designed for embodied intelligence, acting as a "video physics engine." Its architecture, data, and training objectives are specifically tailored for robots and humanoid agents. The primary focus isn't on visual quality or camera movement, but rather ensuring the generated outputs strictly adhere to the laws of physics.
Related event: Ant Group Open-Sources LingBot-Video for Embodied AI(26 posts)→
More from Embodied
- Full teardown: inside Zmotor's 32mm linear actuator for humanoids — MarwaEldiwiny · 2026-10-27
- Full Teardown of a Zmotor Linear Actuator Used in China's Humanoid Robots — MarwaEldiwiny · 2026-10-27
- Video AI agent runs a physics engine, then paints your real room over the blocks — jonstephens85 · 2026-10-27
- World Model Assigns Weight and Friction to Objects, Then Simulates with a Physics Engine — jonstephens85 · 2026-10-27
- First unboxing shots of Apple's foldable "iPhone Duo" surface — chrisfirst · 2026-10-27
- UniAction: unified action conditioning lets one world model handle mixed action types — ZeYanjie · 2026-10-27