BiDex-100 benchmarks bimanual dexterous manipulation across 106 simulation tasks
Each task has an out-of-domain variant, and seven vision-language-action models are scored on 8,080 demonstrations.
3 stories, newest first · one card per story
Each task has an out-of-domain variant, and seven vision-language-action models are scored on 8,080 demonstrations.
DeltaWAM predicts visual deltas and robot actions, raising RoboTwin success while cutting training and inference cost.
ModAR autoregressively denoises multiple future modalities (point tracks, DINO features, depth) before predicting actions, beating prior world-action models at all data scales.
Today 1.6K readers · 2.5K views · 778 reads · all time 189K views