103 citations · 111 across the 9 of their papers we have counts for
3 papers · 1 filter
Patch Policy: Efficient Embodied Control via Dense Visual Representations
Gaoyue Zhou, Zichen Jeff Cui, Ada Langford +3
Pretrained dense visual features from Vision Transformers (ViTs) are powerful yet have been underutilized in robot learning. Modern robot policies either compress each observation…
Beyond Language Modeling: An Exploration of Multimodal Pretraining
Shengbang Tong, David Fan, John Nguyen +18
The visual world offers a critical axis for advancing foundation models beyond language. Despite growing interest in this direction, the design space for native multimodal models r…
Temporal Straightening for Latent Planning
Ying Wang, Oumayma Bounou, Gaoyue Zhou +4
Learning good representations is essential for latent planning with world models. While pretrained visual encoders produce strong semantic visual features, they are not tailored to…