Modality-Autoregressive World-Action Models
ModAR autoregressively denoises multiple future modalities (point tracks, DINO features, depth) before predicting actions, beating prior world-action models at all data scales.
1 stories, newest first · one card per story
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 · 779 reads · all time 189K views