Massive open-source release! LingBot-Video isn't about video quality; it optimizes for physical reasoning, and it runs sparse: only 3B of 30…

Massive open-source release! LingBot-Video isn't about video quality; it optimizes for physical reasoning, and it runs sparse: only 3B of 30B params are active at inference. MoE is finally showing up in long-context video, where inference cost matters a lot. Worth a look. Today we open-source LingBot-Video — the first MoE-based video foundation model built for embodied intelligence. 🔹30B params, only 3B active at inference. 🔹Augmented with 70K hours of embodied data on top of large-scale internet video pretraining. 🔹Already outperforming Wan2.6…

Source: DAIR.AI (X) | 2026-07-08