A lightweight primitive classifier and differentiable guidance mechanism improve pretrained diffusion and flow manipulation policies by 3–7 points at test time without retraining.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2verdicts
CONDITIONAL 2representative citing papers
Projecting robot end-effector state onto image feature maps and sampling co-located visual tokens improves manipulation policy success by 4-10% across 67 tasks.
citing papers explorer
-
PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation
A lightweight primitive classifier and differentiable guidance mechanism improve pretrained diffusion and flow manipulation policies by 3–7 points at test time without retraining.
-
GeoProp: Grounding Robot State in Vision for Generalist Manipulation
Projecting robot end-effector state onto image feature maps and sampling co-located visual tokens improves manipulation policy success by 4-10% across 67 tasks.