VPP2: video-prediction robot policy beats Cosmos3-64B by 11%, tops RoboDojo
lucy_x_shi · x · 2026-10-14
The team behind Video Prediction Policy releases VPP2: a large-scale manipulation-video pretrain of a video foundation model, distilled into a single-step visual planner, plus a mixture-of-transformers inverse-dynamics action module. It outperforms Cosmos3-64B by 11% on instruction-following open-world video prediction and ranks #1 on the RoboDojo Benchmark after post-training, with code and weights open-sourced.
More from Embodied
- Dyna-2 Deep Dive: World-Action Models Trained on 1M Hours of Human Video, 99.4% 24-Hour Autonomy — Latent Space · 2026-10-14
- Nature Will unveils Natura-1: 50B-parameter MoE robot foundation model trained on 1M hours of egocentric human video — rohanpaul_ai · 2026-10-14
- 15 open-source ESP32 AI gadget projects plus a step-by-step Meta Muse SDK flashing tutorial — alexcovo_eth · 2026-10-14
- Collaborative proprioception: Auki gives a phone and robot a shared sense of space — broodsugar · 2026-10-14
- Apple just released a new smart-home command center: should you buy it? — Kiteaton · 2026-10-14
- Physical Intelligence launches Pi API beta for fine-tuning π robotic foundation models — chelseabfinn · 2026-10-14