Conversation Is a Two-Body Problem: Dyadic Evaluation of Full-Duplex Dialogue Models
DyaFDB scores both sides of 7,560 full-duplex model conversations instead of using a fixed examiner.
1 stories, newest first · one card per story
DyaFDB scores both sides of 7,560 full-duplex model conversations instead of using a fixed examiner.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views