Search papers, labs, and topics across Lattice.
Affiliation:
3
0
8
4
CalibDCD reveals that post-training shifts can significantly degrade data contamination detection, but targeted calibration can restore accuracy.
SkillZip achieves a remarkable 3.46x compression ratio while preserving 99.2% of dependencies and 98.7% of verifier reachability, revolutionizing how agent skill libraries can be managed.
$\omega$-0 enables humanoid robots to seamlessly integrate movement and manipulation, outperforming traditional models by predicting coordinated actions directly from sensory inputs.
