Search papers, labs, and topics across Lattice.
2
0
4
33
Achieve 10x faster visuomotor control by shifting iterative refinement from slow inference to efficient training, preserving multimodal action fidelity in single-step robotic manipulation.
VLMs forget less when learning new tasks if you explicitly preserve the semantic relationships they learned during pre-training, especially in vulnerable regions identified with adversarial anchors.
