Conventional flow-based vision-language-action (VLA) models support expressive continuous action generation but rely on multi-step refinement to produce each action chunk, increasing latency in online robot control. To address this issue, we introduce DriftingVLA, a native one-step VLA that generates a complete action...
On-policy distillation (OPD) for WAMs and WAM-OPD are explored and WAM-OPD is introduced, which improves target-task performance while retaining near-initial performance on tasks excluded from adaptation.
P. Liu, Xiao-Han Lei, Shi-Qi Zhang et al.· 0 citations
ReTouch is introduced, a vision-language-action model (VLA) that supports contact-rich dexterous manipulation through tactile predictions continually refined online using execution-time feedback, and keeps tactile predictions aligned with evolving physical interactions, enabling responsive action correction and improvi...
Shi-Qi Zhang, Xin Zhang, Yedong Shen et al.· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.