VideoFDB Benchmark
Explore score history ↗VideoFDB is a benchmark presented for evaluating full-duplex audio-visual conversational agents. It includes 237 dyadic clips with 11 nonverbal conversational dynamics from real-world video calls, along with a taxonomy and rubric-based LM-as-judge evaluation framework.
- Released
- 2026-05-28
- Evaluates
- Cybersecurity, Multimodal, cs.CV
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
VideoFDB paper
No reported scores are on record for this benchmark yet.