3 stories, newest first · one card per story
ENCP calibrates conformal prediction per navigation episode, giving step-level coverage guarantees for vision-language navigation agents despite within-episode dependence.
Researchers introduce HarnessVLN, a zero-shot training-free agent harness that sets new training-free SOTA on vision-language navigation benchmarks including R2R and HM3D.
Researchers present TANGO, a whole-body vision-language-action model enabling humanoid robots to traverse cluttered spaces from language instructions.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views