Same Path, Less Time: Training-Free Fast Execution of Vision-Language-Action Models under Inference Latency
Overview
This research presents Path-preserving Time Scaling (PTS), a training-free execution layer designed for frozen vision-language-action (VLA) models to mitigate the time wasted during inference and slow demonstration speeds.
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 · model-suite combinations tested: 6 other · Basis not reported
“under injected inference latency, PTS raises task throughput over the strongest deployable baseline by 33% for pi0.5 and 104% for SmolVLA while matching or improving the success rate, is best on all six model-suite combinations, and exceeds zero-latency 1x execution. Against asynchronous 1x execution with the same one-step decoder, the time layer alone adds 28% and 38%. On LIBERO-Dynamic it improves on stop-and-wait”
Exact source · revision 1Source owner not reported
Reported quantity · inference latency condition: 1 other · Basis not reported
“arXiv:2611.01390v1 Announce Type: new Abstract: Vision-language-action (VLA) models predict chunks of future actions, yet deployed robots waste time in two ways that are independent of model capability: they halt while the next chunk is inferred, and they move at the speed of slow, cautious demonstrations. Existing remedies remove one loss each, and stacking them fails, because asynchrony and speed-up each change the”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalSame Path, Less Time: Training-Free Fast Execution of Vision-Language-Action Models under Inference Latency
This research presents Path-preserving Time Scaling (PTS), a training-free execution layer designed for frozen vision-language-action (VLA) models to mitigate the time wasted during inference and slow demonstration speeds.
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).