AINeutralarXiv – CS AI · 10h ago6/10
🧠
See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models
Researchers introduce AV-SpeakerBench, a new 3,212-question benchmark designed to evaluate how well multimodal large language models understand audiovisual speech by correlating speakers with their dialogue and timing. Testing reveals Gemini 2.5 Pro significantly outperforms open-source competitors, with the gap primarily attributable to inferior audiovisual fusion capabilities rather than visual perception limitations.
🧠 Gemini