Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method
Paper formalizes multi-agent vision-language navigation and releases the MAVLN benchmark plus TRISS.
3 stories, newest first · one card per story
Paper formalizes multi-agent vision-language navigation and releases the MAVLN benchmark plus TRISS.
PanoVLN uses panoramic views and a 4B backbone to raise VLN success rates.
SatNav is a satellite-imagery UAV vision-language navigation benchmark with 118,000 episodes across 18 cities.
Today 1.3K readers · 2.1K views · 1.6K reads · all time 160K views