Shengshu Tech unveils world model roadmap spanning ViduQ3, ViduS2 and Motus2
生数科技 · wechat · 2026-09-20
Shengshu Tech (Shengshu Technology) announced it was named to Beijing's 2026 Top 100 Private Enterprises lists in both "Tech Innovation" and the newly launched "Future Industry Pioneer" categories, and used the post to lay out its "general world model" strategy with a five-level capability roadmap (L1 world generation to L5 world organizer).
- World generation: ViduQ3 is claimed as the first video model supporting 16-second synchronized audio-video generation, with shot cutting, multi-shot narrative, and Chinese/English/Japanese output;
- World interaction: ViduS2 includes S2-Editing (real-time style/outfit/background swapping) and S2-Avatar (real-time interactive characters), plus exploration of spatial video;
- World action: The robot model Motus2 unifies policy, world simulation, and value evaluation in a video-action model, aiming to move from L3 toward L4 autonomous world agents.
The piece is official PR in tone, but offers a full snapshot of the company's product lines.
More from Embodied
- Shuttered robotics company Eidon AI open-sources 9TB of egocentric video with IMU tracking — vanstriendaniel · 2026-09-21
- FANUC demos a cobot that reroutes around people using RL and NVIDIA cuRobo — lukas_m_ziegler · 2026-09-21
- NeurIPS 2026 EEG/EMG challenge: decode hand pose from wrist EMG with Meta Neural Band — agramfort · 2026-09-21
- Phone video in, navigable 3D room out: K3-powered splat pipeline runs in the browser — willeastcott · 2026-09-21
- World's first human vs. humanoid robot fight held, a 6ft robot steps into the ring — Admirable-Cell-2658 · 2026-09-21
- Sim training in 4.2 GPU-hours teaches robotic hand pen-spinning and cube solving — FinanceYF5 · 2026-09-21