STAR: Steering Action Representations during Inference
Overview
This research introduces STAR, a training-free inference method for vision-language-action models that addresses a grounding gap in late-layer action representations. By applying an exponential moving average over residual updates and adapting mixing strength based on proprioceptive states, STAR improves object awareness without model updates or architectural changes. Experiments show it increases average task success rates by 4.0 percentage points on robot manipulation benchmarks.
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.
Artifact availability · code: available
“ixing when execution dynamics change rapidly. Experiments on robot manipulation benchmarks show that STAR improves late-layer object awareness and increases average task success rates by 4.0 percentage points. Our code is available at https://github.com/PKU-VaLuE-Lab/STAR.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalSTAR: Steering Action Representations during Inference
This research introduces STAR, a training-free inference method for vision-language-action models that addresses a grounding gap in late-layer action representations. By applying an exponential moving average over residual updates and adapting mixing strength based on proprioceptive states, STAR improves object awareness without model updates or architectural changes. Experiments show it increases average task success rates by 4.0 percentage points on robot manipulation benchmarks.
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).