Faster-WAM: Do World Action Models Need Deep Action Modules?
Overview
Faster-WAM replaces deep action modules with a lightweight expert, achieving competitive performance on LIBERO and RoboTwin~2.0 without additional pretraining. It shows faster inference and better generalization under distribution shifts. arXiv:2608.02365v2 Latest: Faster-WAM achieves 3.7× and 1.3× speedups over Fast-WAM and π₀.₅, with lower latency and faster task completion on real robots. arXiv:2608.02365v2
Generated from attributed reports · Updated 1 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · inference speedups: 3.7 other · Basis not reported · Differing source assertions
“oTwin~2.0 without additional embodied pretraining. It provides approximately $3.7\times$ and $1.3\times$ inference speedups over Fast-WAM and $\pi_{0.5}$, respectively. Consistent with its world-model-centric design, Faster-WAM demonstrates stronger generalizability under distribution shifts: the same LIBERO-trained policy achieves $78.3\%$ success on LIBERO-Plus, exceeding Fast-WAM and LingBot-VA by $26.8$ and $8.8$”
Exact source · revision 1Source owner not reported
Reported quantity · inference speedups: 1.3 other · Basis not reported · Differing source assertions
“oTwin~2.0 without additional embodied pretraining. It provides approximately $3.7\times$ and $1.3\times$ inference speedups over Fast-WAM and $\pi_{0.5}$, respectively. Consistent with its world-model-centric design, Faster-WAM demonstrates stronger generalizability under distribution shifts: the same LIBERO-trained policy achieves $78.3\%$ success on LIBERO-Plus, exceeding Fast-WAM and LingBot-VA by $26.8$ and $8.8$”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsFaster-WAM: Do World Action Models Need Deep Action Modules?
This research introduces Faster-WAM, a world-model-centric approach to action prediction that replaces deep action modules with a lightweight expert. The model achieves competitive control performance on LIBERO and RoboTwin~2.0 without additional embodied pretraining, with inference speedups of 3.7× and 1.3× over Fast-WAM and π₀.₅, respectively. It also shows stronger generalization under distribution shifts and comparable real-robot success rates with lower latency and faster task completion.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).