INTACT by ZJU & Tsinghua: Robots Skip Trial-and-Error to Act Directly on Intent
jiqizhixin · x · 2026-08-11
Researchers from Zhejiang University and Tsinghua University introduced INTACT, a novel method that trains world models to map directly from intent to action. This allows robots to skip expensive trial-and-error planning during test time.
Experiments show INTACT achieves a 98.7% success rate (outperforming LeWM CEM's 67%) across four robotics tasks, while running 300x faster at under 6 milliseconds per step.
More from Embodied
- Kyle Vogt's Bot Company Sued for Turning Airbnb into Robot Lab — MarwaEldiwiny · 2026-08-11
- Dyna-2 Model Transfers to WUJI2 Dex Hand, Adapts in 13 Minutes of Data — JasonMa2020 · 2026-08-11
- MIT's GeoPT Model Cuts Simulation Data Needs by 60% with Built-in Physics — nordicinst · 2026-08-11
- MIT and Tsinghua introduce GeoPT: physics as AI's third modality — MIT News AI · 2026-08-11
- Amazon Gutting Nova AI Models, Pivoting Hard to Robotics — max_paperclips · 2026-08-11
- Big Tech Robotics Engineers Make $400K+, Startups Face a Math Problem — ATTlKA · 2026-08-11