Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models
One-word instruction edits swing VLA success sharply; rule-based rephrasing improves frozen policies without retraining.
Stories per day · 30 days
1 RSS
4 stories, newest first · one card per story
Stories tagged #pi0
Exploiting Vulnerabilities: Universal Adversarial Attacks on Vision-Language-Action Models in Robotics
A textured adversarial sphere cuts Pi0 and RDT robot task success by 31.2% to 39.9% in view.
MemBodied: Recurrent Associative Memory for Vision-Language-Action Models
MemBodied gives vision-language-action policies fixed episodic memory without expanding context.
GeoAAC: Geometry-Based Adaptive Action Chunking from Denoising Trajectories in VLA Policies
GeoAAC adaptively sizes action chunking horizons in flow-based VLA policies using denoising trajectory geometry, raising real-world manipulation success from 53.3% to 74.4%.