ImagineNav++ achieves SOTA mapless visual navigation by prompting VLMs to select imagined future views generated from a human-preference-distilled module and maintained via selective foveation memory.
Socratic models: Composing zero-shot multimodal reasoning with language,
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
-
ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination
ImagineNav++ achieves SOTA mapless visual navigation by prompting VLMs to select imagined future views generated from a human-preference-distilled module and maintained via selective foveation memory.