Valency Hub
alphaFeedback
PDF

WorksComputer Science

Replan for Error Recovery: Training Embodied VLMs through Verifiable Interaction with Action-Grouped Turn-GSPO

Zhuoran Wang, Keqing Fan, Yang Li, Jinbo Su, Ke Wang

Published Fresh — added to the Hub within the last 30 daysv1

Publication details
License
CC BY 4.0
Status
Published
AI contributions
  • Generative AI tools
View details
Versions

Every version keeps its own PDF, citation, and review record — endorsements are bound to the version they examined and never carry forward silently.

v1CURRENT
Nov 03, 2026
PUBLISHED
read this version