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.
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
VLA-REPLICA is a low-cost and reproducible real-world benchmark for evaluating VLA models in robotic manipulation tasks.
citing papers explorer
-
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.
-
VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models
VLA-REPLICA is a low-cost and reproducible real-world benchmark for evaluating VLA models in robotic manipulation tasks.