Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
0
OrthoSkillVLA preserves prior skills in pretrained VLA models while seamlessly integrating new ones, outperforming traditional methods in both simulated and real-world scenarios.
Robot control gets a whole lot faster: ProbeFlow slashes action decoding latency by 14.8x in Vision-Language-Action models, all without retraining.
