Search papers, labs, and topics across Lattice.
2
0
5
3
This work proposes SAVLA, an end-to-end symmetry-aware VLA model for robust and data-efficient policy learning, which keeps the pretrained vision-language backbone entirely frozen while combining it with an equivariant flow-matching action head and a learned canonicalizer.
Trusting individual predictions from VLMs can be achieved without fine-tuning, revealing critical insights into model failures that standard self-consistency checks overlook.
