Search papers, labs, and topics across Lattice.
2
0
5
3
Robot control systems are shockingly vulnerable: JailWAM achieves an 84.2% success rate in jailbreaking state-of-the-art World Action Models to perform unsafe physical actions.
Human-in-the-loop learning can now boost dexterous manipulation VLA models by 25%, thanks to a new framework that smartly samples corrective actions and enables real-time intervention.
