G$^3$VLA: Geometric Inductive Bias for Vision-Language-Action Models
Vision-language-action (VLA) models have rapidly advanced generalist robot manipulation by harnessing the semantic knowledge of pretrained vision-language backbones. However, their visual representations are typically grounded in 2D image coordinates rather than calibrated camera geometry. This limitation is especially pronounced in multi-camera systems, where views are coupled by known intrinsics and extrinsics but processed as independent images. We propose G$^3$VLA, a camera-aware geometric module that injects calibrated structure into the visual-token stream of a pretrained VLA without altering its action space or original action-learning objective. G$^3$VLA combines intrinsic-conditi...
| Authors | Yue Peng, Yongzhe Zhao, Artur Habuda et al. |
|---|---|
| Primary category | cs.RO |
| Published | 23 June 2026 |
| Last updated at source | 14 October 2026 |
Popularity, last 2 days
0 now (-9 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
Recent changes
- 17 Oct 2026 Name: G^3VLA: Geometric Inductive Bias for Vision-Language-Action Models → G$^3$VLA: Geometric Inductive Bias for Vision-Language-Action Models
- 17 Oct 2026 Description: Vision-language-action (VLA) models have rapidly advanced generalist robot manipulation by harnessing the semantic knowledge of pretrained vision-language backbones. However, their visual representations are typically grounded in 2D image c → Vision-language-action (VLA) models have rapidly advanced generalist robot manipulation by harnessing the semantic knowledge of pretrained vision-language backbones. However, their visual representations are typically grounded in 2D image c
- 17 Oct 2026 Topics added cs.RO, cs.AI removed hf-daily-papers, vision-language-action models, g³vla, intrinsic-conditioned ray embeddings, projective positional encoding, prope, bidirectional cross-view fusion, point maps, π³x
Changes detected by Silytics between refreshes of the source.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.