/AI4h ago

Stanford's Jeannette Bohg analyzes why VLA models and diffusion policies fail during contact-rich robotic tasks without force sensing

Force-over-time diagrams help categorize precision and force failures.

--0--
Original posts
Comments
Original post
Jeannette Bohg@leto__jean#829inAI

I've always been impressed by how Diffusion policies and VLAs do contact-rich tasks without force sensing.

Today I'll try to Demystify VLA Performance in Contact-Rich Tasks and How to Fix Them.

15:30 at the Act to Sense to Act Better Workshop, Hall C4, #ICRA2026

5:54 AM · Jun 1, 2026 · 2.5K Views
Sentiment
Sentiment unavailable for this story.
Cluster Engagement
-
Views
-
Comments
-
Reposts
-
Bookmarks
Expand data
Posts from X
Most Activity
Most ActivityTimeline
VIEWS266LIKES5
Animesh Garg@animesh_garg

@leto__jean would love to see a recording or your slides. FOMO of not being there!

Jeannette Bohg@leto__jean

I've always been impressed by how Diffusion policies and VLAs do contact-rich tasks without force sensing.

Today I'll try to Demystify VLA Performance in Contact-Rich Tasks and How to Fix Them.

15:30 at the Act to Sense to Act Better Workshop, Hall C4, #ICRA2026

3hViews 266Likes 5Bookmarks 0
Stanford's Jeannette Bohg analyzes why VLA models and diffusion policies fail during contact-rich robotic tasks without force sensing · Digg