SleepWalk is a new three-tier benchmark that evaluates frontier VLMs on instruction-guided trajectory prediction in 3D scenes and finds systematic failures that worsen with task difficulty.
current VLMs are bad at navi- gation
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
-
SleepWalk: A Three-Tier Benchmark for Stress-Testing Instruction-Guided Vision-Language Navigation
SleepWalk is a new three-tier benchmark that evaluates frontier VLMs on instruction-guided trajectory prediction in 3D scenes and finds systematic failures that worsen with task difficulty.