Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Department of Electrical and Microelectronic Engineering, Kate Gleason College of Engineering, Rochester Institute of Technology
3
0
5
LLMs can reliably assess social attraction but tend to exaggerate their judgments compared to human evaluators.
LLM-powered robots misinterpret comfort and strangeness in human-robot interactions, conflating engagement with comfort in their self-assessments.
VINA provides the first theoretical guarantees for INNs and NFs under realistic assumptions, finally bridging the gap between theory and practice for these powerful generative models.