Faster World Action Models for Robotics
open-gigaai · hf · 2026-07-16
This work presents improvements to the World Action Model (WAM) in robot policy learning. The original WAM explicitly generates future videos during inference, which aids action learning but incurs massive overhead, hindering real-time closed-loop control.
The authors propose GigaWorld-Policy-0.5, decoupling training and inference:
- Training Phase: Combines Action-Conditioned World Modeling with WAM training to tightly couple visual dynamics with action representations
- Inference Phase: Performs action decoding only, eliminating future video generation to reduce overhead
- Introduces Mixture-of-Transformers to separate visual dynamics modeling and action generation into specialized experts, boosting inference efficiency
- Employs an agent-based AutoResearch pipeline to automatically search training configurations, minimizing manual tuning
The authors report that this method achieves an action inference latency of 85ms on a local RTX 4090. Experiments and ablations demonstrate enhanced real-time robot control while retaining the training benefits of future visual dynamics.
More from Embodied
- 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
- HandsOn dexterous-manipulation benchmark: best policy 29.1%, GPT-6 Astra just 5.2% — stingning · 2026-10-27
- DexPort: a handheld interface with a real robot hand for dexterous-hand data collection — pabbeel · 2026-10-27
- ROS names Alejandro Hernández Cordero new project lead, eyes 2027 release — ___Mufasaa · 2026-10-27