Search papers, labs, and topics across Lattice.
5
0
6
8
Instruction-following in robot manipulation can be rigorously tested with InstructMove, revealing the true capabilities of VLA models beyond visual cues.
NativeMEM achieves a staggering success rate of 98.7% on real robots by compressing visual histories into single tokens, revolutionizing long-horizon robotic manipulation.
Achieve industrial anomaly detection that not only locates defects, but explains them and generates controlled edits, all in one model.
A 0.2B-parameter VLA model rivals much larger baselines in robotic manipulation, enabling low-latency on-device deployment.
Robots can now learn complex manipulation skills entirely in simulation, thanks to a compositional world model that accurately predicts future states and evaluates progress, leading to a 35-45% performance boost in real-world tasks.
