Showing 2026Show all
2 papers · 1 filter
cs.RO2026
Modality-Autoregressive World-Action Models
Adam Hung, Bardienus P. Duisterhof, Deva Ramanan +1
World-action models (WAMs) jointly model future observations and actions, typically predicting the future as RGB images. Other visual modalities such as depth, pretrained visual fe…
cs.RO2026
3PoinTr: From Human Videos to Robot Policies with 3D Point-Track Plans
Adam Hung, Bardienus Pieter Duisterhof, Jeffrey Ichnowski
Human videos could reduce the reliance on expensive robot demonstrations, but extracting task-relevant features remains challenging. We introduce 3PoinTr, a method that provides ro…