IntentionNav is a new benchmark showing that VLMs infer intended targets from implicit instructions in 48% of cases but achieve only 25% terminal success and 5.5% grounded success in active navigation.
Openfmnav: Towards open-set zero-shot object navi- gation via vision-language foundation models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
IntentionNav: A Benchmark for Intent-Driven Object Navigation from Implicit Human Instruction
IntentionNav is a new benchmark showing that VLMs infer intended targets from implicit instructions in 48% of cases but achieve only 25% terminal success and 5.5% grounded success in active navigation.