A zero-shot MLLM framework decomposes last-mile navigation into view selection, affordance grounding, and base-pose reasoning, achieving SOTA on the OVMM benchmark.
Avoid images where obstacles/clutter block access to the front/edge of the{place recep name}or where approaching the {place recep name}would likely be impossible
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
UniLM-Nav: A Unified Framework for Zero-Shot Last-Mile Navigation
A zero-shot MLLM framework decomposes last-mile navigation into view selection, affordance grounding, and base-pose reasoning, achieving SOTA on the OVMM benchmark.