Search papers, labs, and topics across Lattice.
4
0
8
0
Current multimodal conversational models miss critical emotional cues, revealing a significant gap in their ability to engage in nuanced human-like dialogue.
Discretizing reward models can significantly enhance policy performance by reducing oversensitivity without sacrificing discriminative ability.
The Adaptive Virtual Patient adapts its disclosure behavior in real-time, revealing that therapist exploration is key to enhancing patient engagement during training.
ALMANAC reveals that agents can significantly improve their collaborative competence by learning from detailed human mental model annotations.
