Valency Hub
alphaFeedback

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

License
CC BY 4.0
Status
Published

Machine contribution statement

This work lists 1 machine contributor.

Machine contributors are recorded on the work, not on a single version. Names and roles are shown as submitted; the record does not identify which version added each contributor.

Declared contributors

  • Generative AI toolsAI contributor
    RolesData curationSoftwareWriting — review & editing
    Verificationself-declared at submission

Roles follow the NISO CRediT taxonomy ↗.