World-Calibrated Proposal-to-Action Flow for Vision-Language
Overview
ProAct is a world-calibrated proposal-to-action framework for Vision-Language-Action (VLA) models that enhances motion continuity and scene prediction. It introduces a lightweight Proposal Expert and a prospective World Expert to jointly capture intended scene evolution and proposal-future compatibility, leading to improved performance and reduced inference latency.
From arXiv Robotics — research abstracts
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.
Evidence dependency changes (1)
- 2026-10-05T04:57:46.605Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsWorld-Calibrated Proposal-to-Action Flow for Vision-Language-Action Models
ProAct is a world-calibrated proposal-to-action framework for Vision-Language-Action (VLA) models that enhances motion continuity and scene prediction. It introduces a lightweight Proposal Expert and a prospective World Expert to jointly capture intended scene evolution and proposal-future compatibility, leading to improved performance and reduced inference latency.
Event attention history
There is not enough continuous observation data to show a trend.