Search papers, labs, and topics across Lattice.
3
0
4
34
FutureRTC transforms real-time robot execution by seamlessly predicting execution-time observations, leading to smoother and faster task performance even under inference delays.
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.
