Latent Interface Training breaks vision-action shortcuts in VLA and WAM training

DJiafei · x · 2026-09-11

Introducing Latent Interface Training (LIT): action experts in VLAs and WAMs can learn vision-action shortcuts that undermine out-of-distribution generalization. LIT's approach: learn to act first, then learn how to use vision.

Related event: LIT Breaks Vision-Action Shortcuts in Robot VLA Models(4 posts)→

Original post →

More from Embodied

Embodied channel →