WoMAP generates training data from Gaussian Splatting scenes, distills detector confidence into a latent world model, and uses that model to refine vision-language action proposals for open-vocabulary object localization.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
WoMAP: World Models For Embodied Open-Vocabulary Object Localization
WoMAP generates training data from Gaussian Splatting scenes, distills detector confidence into a latent world model, and uses that model to refine vision-language action proposals for open-vocabulary object localization.