The paper quantifies the geometric gap in current VLAs via linear probing and compares three architectures for injecting geometry from GFMs while analyzing impacts of data, cameras, and reconstruction quality.
arXiv preprint arXiv:2509.20297 (2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models
The paper quantifies the geometric gap in current VLAs via linear probing and compares three architectures for injecting geometry from GFMs while analyzing impacts of data, cameras, and reconstruction quality.