Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
Deeper reasoning creates an unexpected safety backdoor: extended CoT dilutes attention away from system constraints, making models progressively more vulnerable to jailbreaks the longer they "think."
Robots can now mimic human dexterity more effectively by learning to apply the right forces during manipulation, bridging the gap between human demonstrations and robotic actions.
