ResWAM: residual learning on frozen DINOv3 boosts VLA success with less compute

OPTML-Group · hf · 2026-11-18

ResWAM targets World-Action Models by learning visual residuals on frozen DINOv3 features — modeling what changes rather than what stays — combined with a lightweight dual-branch DiT trained via conditional flow matching, improving vision-language-action policy success while lowering training and inference compute.

Original post →

More from Embodied

Embodied channel →