Open-Source Embodied Video Foundation Model
nikola_mr64990 · x · 2026-07-09
Robbyant has open-sourced LingBot-Video, an embodied intelligence video foundation model utilizing a MoE architecture with 30B total parameters, of which only 3B are activated during inference. The model builds on large-scale internet video pre-training, supplemented with 70,000 hours of embodied data. The post claims it outperforms Wan2.6, Seedance 1.5 Pro, and Cosmos3 Super on RBench, aiming to accelerate the deployment of embodied applications like robotics.
Related event: Ant Group Open-Sources LingBot-Video for Embodied AI(26 posts)→
More from Embodied
- WanGP v18.81 adds Tencent's Hy-Nomas world model, playable on 8GB VRAM — cocktailpeanut · 2026-10-27
- NVIDIA open-sources FLORA, a robotics data engine ~125x cheaper than GPT-6 Astra — nvidia · 2026-10-27
- Embodied AI startups need a different operational discipline, investor says — ___Mufasaa · 2026-10-27
- π0.5 study: raising demos from 10 to 438 lifts Place Ball in Bowl success from 7% to 83% — stingning · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27
- HandsOn benchmark: 66 verified tasks and 18,000 human demos for dexterous manipulation — stingning · 2026-10-27