VEGA improves spatial reasoning in VLA models for robotics by aligning visual encoder features with 3D-supervised DINOv2 representations via a temporary projector and cosine similarity loss.
Pointvla: Injecting the 3d world into vision-language-action models.IEEE Robotics and Automation Letters, 11(3):2506–2513
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 2years
2026 2roles
background 1polarities
background 1representative citing papers
VLA benchmark success rates cannot distinguish semantic generalization from physical reasoning due to an identifiability gap in current evaluation protocols.
citing papers explorer
-
VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models
VEGA improves spatial reasoning in VLA models for robotics by aligning visual encoder features with 3D-supervised DINOv2 representations via a temporary projector and cosine similarity loss.
-
Position: Vision-Language-Action Models Cannot Be Verified to Perform Physical Reasoning
VLA benchmark success rates cannot distinguish semantic generalization from physical reasoning due to an identifiability gap in current evaluation protocols.