Axiom-0: Hierarchical Self-Refinement for Vision-Language-Action Policies
Overview
Axiom-0 improves task generalization through hierarchical self-refinement, achieving 62.32% success on RoboCasa365, outperforming Paimon-0 and Xiaomi-Robotics-1 by 4.22 and 4.92 points respectively, with minimal latency increase.
Generated from attributed reports · Updated 2 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.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsAxiom-0: Hierarchical Self-Refinement for Vision-Language-Action Policies
Axiom-0 is a vision-language-action (VLA) policy that enhances task generalization through hierarchical self-refinement. It improves representation quality and action generation via intra-VLM representation refinement and VLM-action interface refinement. On RoboCasa365, it achieves 62.32% overall success, surpassing Paimon-0 by 4.22 percentage points and Xiaomi-Robotics-1 by 4.92 points, with only a 1.7% increase in action-chunk generation latency.
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).