Search papers, labs, and topics across Lattice.
Affiliation:
3
0
7
3
Adversarial attacks can be mitigated by up to 60% in Mixture-of-Experts models through a novel shared expert mechanism that anchors safety alignment.
Current NLP metrics for "trustworthy" AI in mental health are dangerously misaligned with the actual needs of patients and practitioners.
Ditch the eye-tracking hardware: This RGB-camera-based gaze detection system lets robots intuitively understand task progression by simply watching where you look.
