ERVLA: Vision-Language-Action Model for Generalizable Robot Manipulation
Overview
This research explores embodied chain-of-thought (CoT) for robotic control, introducing ERVLA, a vision-language-action model that effectively integrates linguistic reasoning into robot manipulation. ERVLA uses a CoT-dropout strategy during training and predicts actions directly during inference, achieving 86.9% success on LIBERO-Plus and 53.2% on VLABench, with superior performance in out-of-distribution settings.
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.
Reported quantity · Robot trajectories: 978743 trajectories · trajectory count
“arXiv:2606.03784v3 Announce Type: replace Abstract: Embodied chain-of-thought (CoT) aims to bridge linguistic reasoning with robotic control, yet its effective form and integration remain underexplored. In this paper, we revisit embodied CoT for robotic control at an unprecedented scale. We curate the largest embodied CoT corpus to date, comprising 978,743 trajectories, 226.3M samples, and 2592.5 hours of data. Throu”
Exact source · revision 1Source owner not reported
Reported quantity · samples: 226300000 other · Basis not reported
“arXiv:2606.03784v3 Announce Type: replace Abstract: Embodied chain-of-thought (CoT) aims to bridge linguistic reasoning with robotic control, yet its effective form and integration remain underexplored. In this paper, we revisit embodied CoT for robotic control at an unprecedented scale. We curate the largest embodied CoT corpus to date, comprising 978,743 trajectories, 226.3M samples, and 2592.5 hours of data. Throu”
Exact source · revision 1Source owner not reported
Reported quantity · data: 2592.5 hours · Basis not reported
“arXiv:2606.03784v3 Announce Type: replace Abstract: Embodied chain-of-thought (CoT) aims to bridge linguistic reasoning with robotic control, yet its effective form and integration remain underexplored. In this paper, we revisit embodied CoT for robotic control at an unprecedented scale. We curate the largest embodied CoT corpus to date, comprising 978,743 trajectories, 226.3M samples, and 2592.5 hours of data. Throu”
Exact source · revision 1Source owner not reported
Evidence dependency changes (2)
- 2026-10-30T22:49:57.699Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T22:49:39.558Z · 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 abstractsSignalRevisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation
This research explores embodied chain-of-thought (CoT) for robotic control, introducing ERVLA, a vision-language-action model that effectively integrates linguistic reasoning into robot manipulation. ERVLA uses a CoT-dropout strategy during training and predicts actions directly during inference, achieving 86.9% success on LIBERO-Plus and 53.2% on VLABench, with superior performance in out-of-distribution settings.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).