ByteDance preps real-time spatial video world model, Zhang Yiming personally overseeing, Bloomberg reports
智东西 · wechat · 2026-09-08
ByteDance is preparing to launch an AI model for real-time spatial video generation as soon as next month, with founder Zhang Yiming personally coordinating AI resources and compute across business units, Bloomberg reports citing sources.
- Built on ByteDance's Seedance video model, it aims to create interactive virtual worlds for livestreaming, short dramas, and games, pushing ByteDance into the emerging "world model" field alongside Google's Genie
- Positioned as a flywheel linking ByteDance's AI models, cloud, content platforms, and PICO XR hardware: generating video responsive to headset users' voice and motion at 0.05s latency and 20fps
- Offloading generation to the cloud would cut PICO headset compute needs and cost, paving the way for lighter hardware; PICO Space Pro was delayed to Q4 and appears to have passed FCC certification
- Bloomberg sees VR competition shifting from hardware specs to AI models, compute, and content distribution; ByteDance recently secured $29.6B in loans for AI expansion
Related event: ByteDance Secretly Builds Real-Time World Model Under Zhang Yiming(4 posts)→
More from Embodied
- Montreal Robotics Summer School trains Unitree Go1 to autonomously hunt its food bowl — GlenBerseth · 2026-09-09
- Agility Robotics' humanoid Digit is now available to buy or rent — heatherknight · 2026-09-09
- This AI Denim Jacket Remembers Who You Talked To — Scobleizer · 2026-09-09
- Analyst breaks down Agility robot economics: $100k price struggles to beat human labor costs — MatthewChang · 2026-09-09
- Antioch raises $32M Series A led by Greylock to bring software-speed simulation to physical AI testing — thetripathi58 · 2026-09-09
- Deft Robotics launches unified deployment platform for physical AI — Scobleizer · 2026-09-09